© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 425
    Prev
    Next
    INDEX
    Explanations

    verbs related to dependency or trust

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    311
    +0.12
    0.5%
    283
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.12
    0.01
    283
    +0.11
    0.01
    448
    +0.11
    0.02
    Negative Logits
    corn
    -0.77
    vision
    -0.68
    sell
    -0.67
     Scotia
    -0.65
    cell
    -0.64
    nick
    -0.64
    lat
    -0.62
    vals
    -0.62
    cel
    -0.61
    tha
    -0.61
    POSITIVE LOGITS
     upon
    1.02
     heavily
    0.99
    lessly
    0.95
     solely
    0.93
    ENCY
    0.88
    encies
    0.86
    enza
    0.83
    ences
    0.81
     rely
    0.81
    gency
    0.79
    Activations Density 0.043%

    No Known Activations