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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1654
    Prev
    Next
    INDEX
    Explanations

    text related to sports, statistics, and competition

    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
    87
    +0.40
    2.2%
    459
    +0.13
    0.7%
    756
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.40
    -0.07
    756
    +0.13
    -0.09
    459
    +0.12
    0.15
    Negative Logits
    DCS
    -0.53
    î
    -0.53
    cigarettes
    -0.49
    abetes
    -0.49
    annabin
    -0.49
    "))
    -0.47
    Gender
    -0.47
    Ħ¢
    -0.45
     Copyright
    -0.45
    AFP
    -0.45
    POSITIVE LOGITS
     however
    1.13
     meanwhile
    0.99
     moreover
    0.92
     therefore
    0.86
    anwhile
    0.78
     though
    0.78
     furthermore
    0.77
     likewise
    0.61
     also
    0.61
     additionally
    0.60
    Activations Density 9.272%

    No Known Activations