Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 511
    Prev
    Next
    INDEX
    Explanations

    speed or velocity metrics and measurements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    456
    +0.14
    0.5%
    167
    +0.14
    0.5%
    163
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.10
    326
    +0.14
    0.13
    232
    +0.13
    0.07
    Negative Logits
    NetMessage
    -1.33
    ciating
    -0.91
    lihood
    -0.88
    ivity
    -0.87
    keyes
    -0.86
    piece
    -0.83
     Strongh
    -0.83
    acia
    -0.83
    reen
    -0.83
    creen
    -0.82
    POSITIVE LOGITS
    enance
    1.27
    ãĤ¡
    1.25
    inary
    1.11
     Weinstein
    1.04
    awei
    1.00
    aku
    0.96
    iquette
    0.94
    ãĥĺ
    0.94
    ahime
    0.93
     GOODMAN
    0.92
    Activations Density 2.575%

    No Known Activations