© 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. 704
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals and current 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_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
    659
    +0.15
    0.7%
    519
    +0.12
    0.6%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.03
    519
    +0.12
    0.02
    232
    +0.09
    0.02
    Negative Logits
    llor
    -0.73
     mandatory
    -0.66
    Reloaded
    -0.65
     margins
    -0.65
     td
    -0.63
     unaccount
    -0.63
     outgoing
    -0.62
    CLASSIFIED
    -0.62
     lone
    -0.61
     penalties
    -0.60
    POSITIVE LOGITS
    zig
    1.26
    forth
    1.25
    ube
    1.04
    coni
    1.00
    ilo
    0.98
     Marino
    0.94
    alog
    0.94
     Rather
    0.93
    wei
    0.93
    vier
    0.91
    Activations Density 0.044%

    No Known Activations