© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7464
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of different types of warriors throughout various contexts, including historical, mythological, and fictional

    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
    247
    +0.15
    0.7%
    288
    +0.14
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.03
    247
    +0.14
    0.02
    326
    +0.12
    0.02
    Negative Logits
    uate
    -0.85
    orage
    -0.79
    ories
    -0.79
    changes
    -0.75
    ions
    -0.74
    ibly
    -0.71
    upon
    -0.70
    ascript
    -0.69
    urations
    -0.68
    ĸļ
    -0.67
    POSITIVE LOGITS
    riors
    1.35
    rior
    1.33
    ¯¯¯¯
    0.94
    fare
    0.89
    ¯¯¯¯¯¯¯¯
    0.85
     warriors
    0.84
    ¯¯
    0.83
    hip
    0.82
     warrior
    0.81
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.77
    Activations Density 0.062%

    No Known Activations