© 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 12288
    9. 8-RES_FS12288-JB
    11. 366
    Prev
    Next
    INDEX
    Explanations

    references to vulnerabilities in systems or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    99
    +0.16
    0.7%
    288
    +0.12
    0.6%
    285
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.16
    0.02
    151
    +0.12
    0.03
    417
    +0.12
    0.02
    Negative Logits
    zos
    -0.72
    rows
    -0.71
    corn
    -0.69
    inth
    -0.68
    Maker
    -0.66
    row
    -0.64
     Wolver
    -0.64
    ALSE
    -0.63
    fare
    -0.63
    zzi
    -0.63
    POSITIVE LOGITS
     vulnerable
    0.89
     sensitive
    0.85
    ivities
    0.83
    mble
    0.79
     sensit
    0.77
     embr
    0.74
     vulner
    0.73
     proble
    0.72
    wcs
    0.70
     vulnerability
    0.69
    Activations Density 0.069%

    No Known Activations