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

    Neuronpedia

    Jacobian LensNEW
    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. 33503
    Prev
    Next
    INDEX
    Explanations

    mentions of topics, categories, and keywords related to research, agriculture, technology, and politics within a document

    oai_token-act-pair · gpt-3.5-turbo
    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
    +0.10
    0.5%
    371
    +0.10
    0.5%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.22
    6
    +0.10
    0.14
    214
    +0.09
    0.06
    Negative Logits
    IELD
    -0.67
    rier
    -0.65
     chain
    -0.65
     subsequ
    -0.64
    rine
    -0.60
     chains
    -0.60
     equivalents
    -0.59
     depended
    -0.57
     branches
    -0.57
    rites
    -0.56
    POSITIVE LOGITS
     POLIT
    0.68
     Cosponsors
    0.66
    business
    0.64
     Various
    0.61
    ategories
    0.59
    hern
    0.59
    Topics
    0.59
    latest
    0.59
    crime
    0.59
    econom
    0.58
    Activations Density 7.695%

    No Known Activations