© 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. 18857
    Prev
    Next
    INDEX
    Explanations

    phrases related to sovereignty or authority

    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
    756
    +0.14
    0.7%
    442
    +0.12
    0.5%
    103
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.14
    0.01
    55
    +0.12
    0.02
    449
    +0.11
    0.01
    Negative Logits
     vigilance
    -0.62
     reservation
    -0.62
     bowel
    -0.61
     fluor
    -0.59
     Marble
    -0.58
     ultras
    -0.57
     fertility
    -0.56
     tert
    -0.56
     Bryce
    -0.56
     Polo
    -0.56
    POSITIVE LOGITS
    ndra
    0.93
    ignty
    0.79
    orah
    0.78
    soType
    0.77
    ymm
    0.76
    vre
    0.75
    hesive
    0.75
    wine
    0.72
    yang
    0.71
    eous
    0.70
    Activations Density 0.056%

    No Known Activations