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

    Neuronpedia

    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. 8025
    Prev
    Next
    INDEX
    Explanations

    mentions of healthcare, medical errors, and risk assessment

    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
    195
    +0.15
    0.7%
    113
    +0.10
    0.4%
    588
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.15
    0.01
    682
    +0.10
    0.01
    588
    +0.10
    0.01
    Negative Logits
    culosis
    -0.79
     tuberculosis
    -0.73
     bearer
    -0.67
    anza
    -0.67
    Reviewer
    -0.65
     Wand
    -0.63
     modem
    -0.62
    FUL
    -0.61
     Archdemon
    -0.61
     Jackets
    -0.61
    POSITIVE LOGITS
    arate
    1.42
    aration
    1.31
    arations
    1.09
    arat
    1.05
    aret
    0.92
    ay
    0.91
    sis
    0.87
    rees
    0.84
    ared
    0.84
    hew
    0.84
    Activations Density 0.012%

    No Known Activations