© 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. 9814
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts associated with support or posture

    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
    83
    +0.12
    0.5%
    343
    +0.09
    0.4%
    356
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.03
    288
    +0.09
    0.04
    326
    +0.09
    0.03
    Negative Logits
    ophon
    -0.98
    ging
    -0.98
    ical
    -0.91
    aeus
    -0.89
    atile
    -0.84
    STER
    -0.83
    ktop
    -0.81
    yrinth
    -0.80
    iary
    -0.80
    ococ
    -0.80
    POSITIVE LOGITS
     Clinic
    1.05
     Cavaliers
    0.85
     blades
    0.84
     Yard
    0.83
     Indians
    0.76
    ãĥ£
    0.75
    ieri
    0.73
     straps
    0.71
     Leafs
    0.71
    ockey
    0.67
    Activations Density 0.170%

    No Known Activations