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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2622
    Prev
    Next
    INDEX
    Explanations

    names and possibly company/product related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    324
    +0.12
    0.5%
    425
    +0.11
    0.5%
    154
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.12
    0.08
    177
    +0.11
    0.07
    324
    +0.10
    0.07
    Negative Logits
    ©¶æ¥µ
    -0.67
    Ĥª
    -0.60
    ŃĶ
    -0.57
     LET
    -0.55
    ");
    -0.54
    ENCY
    -0.54
    ');
    -0.53
    '';
    -0.52
    @#
    -0.52
     consequently
    -0.52
    POSITIVE LOGITS
     nor
    0.94
     and
    0.93
     AND
    0.82
     versus
    0.79
     vs
    0.64
     or
    0.63
    ring
    0.58
    ortium
    0.58
     sexes
    0.57
    athed
    0.56
    Activations Density 2.070%

    No Known Activations