© 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 49152
    9. 8-RES_FS49152-JB
    11. 26519
    Prev
    Next
    INDEX
    Explanations

    passages discussing political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    679
    +0.17
    0.8%
    640
    +0.14
    0.7%
    430
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.17
    0.05
    430
    +0.14
    0.05
    6
    +0.13
    0.05
    Negative Logits
     stamped
    -0.93
     extinguished
    -0.85
     punch
    -0.81
     ration
    -0.71
     stamp
    -0.68
     fade
    -0.68
     coughing
    -0.68
     manoeuv
    -0.68
     brawl
    -0.66
     taunt
    -0.66
    POSITIVE LOGITS
     Previously
    1.26
     Currently
    1.20
     Originally
    1.08
     She
    1.04
     He
    1.03
     Serving
    1.02
     His
    1.01
     Recently
    0.98
     Born
    0.97
     Prior
    0.94
    Activations Density 0.134%

    No Known Activations