© 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 24576
    9. 8-RES_FS24576-JB
    11. 19863
    Prev
    Next
    INDEX
    Explanations

    content related to political topics and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    385
    +0.14
    0.6%
    489
    +0.10
    0.5%
    524
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.14
    0.02
    164
    +0.10
    0.02
    385
    +0.10
    0.02
    Negative Logits
    alis
    -0.78
    ixel
    -0.78
    worms
    -0.75
    chenko
    -0.73
    eele
    -0.72
    enance
    -0.72
    anium
    -0.72
    ifts
    -0.72
    ubes
    -0.72
    ypes
    -0.71
    POSITIVE LOGITS
    cffff
    0.85
    ··
    0.85
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.74
    ////////////////////////////////
    0.74
     Recap
    0.71
     Edited
    0.70
     |--
    0.69
     Reached
    0.69
    Mah
    0.68
    âĢ¢âĢ¢
    0.68
    Activations Density 0.014%

    No Known Activations