© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45693
    Prev
    Next
    INDEX
    Explanations

    intensity descriptors related to competition or conflict

    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
    10
    +0.10
    0.5%
    130
    +0.10
    0.4%
    730
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.10
    0.01
    117
    +0.10
    0.01
    730
    +0.09
    0.01
    Negative Logits
    ulhu
    -0.92
    uration
    -0.82
    urated
    -0.79
    ablish
    -0.73
    isphere
    -0.71
     Peb
    -0.70
    代
    -0.69
    abad
    -0.68
    ammy
    -0.68
    roma
    -0.68
    POSITIVE LOGITS
     competitor
    0.93
    ly
    0.91
     competition
    0.91
     battle
    0.85
     critic
    0.84
     fierce
    0.83
     competitive
    0.82
     battles
    0.82
    tails
    0.80
     antic
    0.80
    Activations Density 0.015%

    No Known Activations