© 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. 10202
    Prev
    Next
    INDEX
    Explanations

    mentions of characters and details related to certain TV series

    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
    430
    +0.12
    0.5%
    223
    +0.10
    0.5%
    456
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.02
    430
    +0.10
    0.02
    628
    +0.10
    0.02
    Negative Logits
     chorus
    -0.68
    tera
    -0.66
     Intermediate
    -0.64
    perm
    -0.64
    lag
    -0.63
     envelope
    -0.61
    FUL
    -0.61
     total
    -0.60
    restricted
    -0.58
     actionGroup
    -0.57
    POSITIVE LOGITS
    sonian
    1.01
    ysis
    0.91
     Who
    0.88
    taining
    0.85
    ates
    0.84
    ate
    0.81
    abase
    0.78
    ial
    0.78
    ately
    0.78
    ocide
    0.77
    Activations Density 0.064%

    No Known Activations