© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    mentions of authority figures or legal actions

    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
    691
    +0.10
    0.4%
    496
    +0.10
    0.4%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.10
    0.04
    225
    +0.10
    0.04
    278
    +0.09
    0.04
    Negative Logits
    tackle
    -0.71
     Reson
    -0.64
    mostly
    -0.61
     horm
    -0.60
    leted
    -0.60
    Goal
    -0.58
    Tip
    -0.58
    igr
    -0.55
     Trop
    -0.55
     Hits
    -0.55
    POSITIVE LOGITS
     anything
    1.22
    chard
    1.11
     any
    1.09
    nam
    1.04
    acles
    1.03
     nor
    1.03
     else
    1.02
     anymore
    1.02
    Else
    1.01
     whatsoever
    0.98
    Activations Density 0.141%

    No Known Activations