© 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 1536
    9. 8-RES_FS1536-JB
    11. 1037
    Prev
    Next
    INDEX
    Explanations

    words related to medical studies and health, specifically focusing on metabolic profiles and weight loss impacts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    433
    +0.11
    0.5%
    202
    +0.10
    0.5%
    282
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.15
    232
    +0.10
    0.09
    343
    +0.10
    0.08
    Negative Logits
    listed
    -0.71
    -|
    -0.70
    rians
    -0.68
     coh
    -0.67
    allow
    -0.65
    ¯¯¯¯¯¯¯¯
    -0.64
    ird
    -0.63
    owship
    -0.63
    worthiness
    -0.60
    liner
    -0.60
    POSITIVE LOGITS
    ozo
    0.98
    asus
    0.96
    sylvania
    0.93
    emonium
    0.85
    asant
    0.83
    insula
    0.82
    OTUS
    0.82
    ublic
    0.82
    ongyang
    0.81
    atern
    0.81
    Activations Density 2.395%

    No Known Activations