© 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. 19877
    Prev
    Next
    INDEX
    Explanations

    years mentioned in historical contexts

    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
    744
    +0.10
    0.5%
    598
    +0.10
    0.5%
    542
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.10
    0.04
    542
    +0.10
    0.03
    73
    +0.10
    0.03
    Negative Logits
    parency
    -0.71
    venge
    -0.71
    edo
    -0.71
    hed
    -0.69
     verbs
    -0.65
     impunity
    -0.62
    inventoryQuantity
    -0.62
    resso
    -0.61
    iqu
    -0.61
    prime
    -0.61
    POSITIVE LOGITS
    -'
    0.78
    å¹
    0.74
    çļ
    0.70
     onwards
    0.66
     Reich
    0.65
     Sakuya
    0.65
    1945
    0.65
     Bomber
    0.65
     Reincarn
    0.65
     MacArthur
    0.64
    Activations Density 0.038%

    No Known Activations