© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26619
    Prev
    Next
    INDEX
    Explanations

    instances of physical violence or injury

    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
    362
    +0.11
    0.5%
    587
    +0.10
    0.5%
    97
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.11
    0.02
    362
    +0.10
    0.02
    587
    +0.10
    0.02
    Negative Logits
    ghai
    -0.71
    igne
    -0.69
    shire
    -0.66
    âĨij
    -0.65
    ablishment
    -0.65
    ilight
    -0.65
    amental
    -0.63
    idity
    -0.63
    former
    -0.61
    iance
    -0.60
    POSITIVE LOGITS
     impunity
    1.08
     gunfire
    0.96
     gust
    0.95
     fists
    0.90
     regards
    0.87
     bullets
    0.86
    stood
    0.85
     arrows
    0.83
     scissors
    0.82
     missiles
    0.81
    Activations Density 0.047%

    No Known Activations