© 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. 37204
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and governmental oversight

    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
    640
    +0.29
    1.4%
    373
    +0.14
    0.7%
    480
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.11
    94
    +0.14
    0.07
    143
    +0.12
    0.06
    Negative Logits
     awa
    -0.65
     endeav
    -0.65
    iton
    -0.64
     dissu
    -0.63
     wanting
    -0.63
    xual
    -0.63
    lihood
    -0.62
     naming
    -0.61
     Cyborg
    -0.60
     next
    -0.60
    POSITIVE LOGITS
    ³³³³³³³³
    0.96
    Posted
    0.90
    WASHINGTON
    0.88
    ³³³³
    0.87
    PORT
    0.84
    ³³³³³³³³³³³³³³³³
    0.83
    DEN
    0.82
    ramid
    0.81
    arta
    0.81
    MI
    0.80
    Activations Density 0.220%

    No Known Activations