© 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 EvalsExportsinterp-engineNEWAPI 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. 36695
    Prev
    Next
    INDEX
    Explanations

    reviews and discussions about specific products or subjects

    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
    +0.26
    1.3%
    393
    +0.20
    1.0%
    159
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.26
    0.29
    159
    +0.20
    0.18
    384
    +0.13
    0.11
    Negative Logits
    isms
    -0.76
    ©¶æ¥µ
    -0.74
    lev
    -0.73
    iberal
    -0.70
     ILCS
    -0.66
    arson
    -0.66
    istries
    -0.66
    ques
    -0.66
    respons
    -0.65
    tones
    -0.65
    POSITIVE LOGITS
     guy
    0.87
     particular
    0.86
     trope
    0.86
     nifty
    0.78
     lowly
    0.78
     iteration
    0.78
     newest
    0.77
     week
    0.76
     gist
    0.76
     latest
    0.74
    Activations Density 11.045%

    No Known Activations