© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 39742
    Prev
    Next
    INDEX
    Explanations

    information related to written content such as blog posts, articles, and updates

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and elements of syntax such as conjunctions and particles, often in contexts indicating transitions or connections within sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.14
    0.6%
    679
    +0.12
    0.6%
    358
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.36
    640
    +0.12
    0.33
    679
    +0.10
    0.29
    Negative Logits
    untarily
    -0.65
    atics
    -0.62
    unts
    -0.61
     footing
    -0.60
    ht
    -0.60
    htar
    -0.57
    animate
    -0.57
    iola
    -0.57
     electromagnetic
    -0.57
     Cot
    -0.57
    POSITIVE LOGITS
     summarizes
    0.72
     headlined
    0.71
     titled
    0.70
     summar
    0.69
     Column
    0.68
     Readers
    0.67
     Editorial
    0.66
     reproduced
    0.66
     edited
    0.66
     <+
    0.66
    Activations Density 19.762%

    No Known Activations