© 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. 18848
    Prev
    Next
    INDEX
    Explanations

    titles and honorifics before names in text

    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
    430
    +0.14
    0.7%
    408
    +0.13
    0.6%
    715
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.05
    232
    +0.13
    0.04
    541
    +0.12
    0.03
    Negative Logits
    irtual
    -0.88
    hello
    -0.83
    mble
    -0.81
    Ü
    -0.79
    Reviewer
    -0.78
    Psy
    -0.77
    DVD
    -0.77
    LET
    -0.76
    SAN
    -0.76
    comed
    -0.76
    POSITIVE LOGITS
     Hyde
    1.05
     Abbott
    0.95
     Fernandez
    0.90
     Sark
    0.88
     Flores
    0.87
     Fla
    0.86
     Kurd
    0.86
     Hollande
    0.86
     Bou
    0.86
     Duterte
    0.84
    Activations Density 0.060%

    No Known Activations