© 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. 18946
    Prev
    Next
    INDEX
    Explanations

    action words pertaining to challenging or breaking norms

    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
    409
    +0.10
    0.4%
    235
    +0.09
    0.4%
    246
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.05
    608
    +0.09
    0.06
    669
    +0.09
    0.04
    Negative Logits
    Solution
    -0.81
    pmwiki
    -0.77
    kas
    -0.73
     Nanto
    -0.70
     Solution
    -0.70
     consulted
    -0.68
    assets
    -0.68
    emed
    -0.66
    umerable
    -0.66
     avail
    -0.65
    POSITIVE LOGITS
     precon
    1.07
     stereotypes
    1.04
     misconceptions
    1.02
     adversity
    1.02
     poverty
    0.95
     clutter
    0.94
     stigma
    0.94
     oppressive
    0.92
     tyranny
    0.90
     inequalities
    0.89
    Activations Density 0.369%

    No Known Activations