© 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. 46073
    Prev
    Next
    INDEX
    Explanations

    phrases containing the phrase "some sort of."

    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
    332
    +0.14
    0.5%
    649
    +0.13
    0.5%
    424
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.14
    0.11
    408
    +0.13
    0.14
    227
    +0.13
    0.04
    Negative Logits
    sbm
    -0.93
    aughs
    -0.91
     Pigs
    -0.85
    oons
    -0.85
    users
    -0.85
     Tackle
    -0.85
     Files
    -0.83
    Phones
    -0.82
     VIDEOS
    -0.82
     Scrib
    -0.81
    POSITIVE LOGITS
    icipated
    0.93
     somew
    0.92
     unspecified
    0.89
     semblance
    0.87
     miraculous
    0.82
     fuzzy
    0.82
     intermediary
    0.81
     proportional
    0.80
     resembling
    0.80
     recognizable
    0.79
    Activations Density 8.387%

    No Known Activations