© 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. 41780
    Prev
    Next
    INDEX
    Explanations

    mentions of game leads and deficits in competitive contexts

    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
    225
    +0.10
    0.4%
    585
    +0.09
    0.4%
    39
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.10
    0.01
    259
    +0.09
    0.01
    391
    +0.09
    0.01
    Negative Logits
     concess
    -0.89
    ROR
    -0.65
    entric
    -0.63
    wagen
    -0.63
     recip
    -0.61
    tein
    -0.61
    ombies
    -0.61
     representations
    -0.61
    irlf
    -0.59
     loopholes
    -0.59
    POSITIVE LOGITS
    hunter
    0.85
    less
    0.78
    better
    0.76
    ership
    0.75
    wall
    0.74
    drawn
    0.72
    manship
    0.72
    lines
    0.70
    now
    0.70
    lessness
    0.70
    Activations Density 0.012%

    No Known Activations