© 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. 26590
    Prev
    Next
    INDEX
    Explanations

    mentions of the group Boko Haram and references to Alibaba

    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
    481
    +0.13
    0.6%
    288
    +0.13
    0.6%
    359
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.13
    0.01
    359
    +0.13
    0.01
    621
    +0.11
    0.01
    Negative Logits
    mble
    -0.89
     Yosemite
    -0.71
    Reviewer
    -0.71
    retion
    -0.68
    bnb
    -0.68
    enegger
    -0.67
    FTWARE
    -0.67
     Apollo
    -0.64
    tainment
    -0.63
    eric
    -0.63
    POSITIVE LOGITS
     Haram
    1.56
    zeb
    0.88
    aku
    0.85
    ¯
    0.83
    unin
    0.83
    ju
    0.76
    ame
    0.76
    amous
    0.74
    Ń
    0.74
    ¹
    0.73
    Activations Density 0.005%

    No Known Activations