© 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 49152
    9. 8-RES_FS49152-JB
    11. 25828
    Prev
    Next
    INDEX
    Explanations

    terms related to health measurements and their correlations to various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    333
    +0.12
    0.5%
    450
    +0.11
    0.5%
    415
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.12
    0.02
    455
    +0.11
    0.03
    252
    +0.10
    0.02
    Negative Logits
    apers
    -0.86
    cloth
    -0.76
     loopholes
    -0.71
    places
    -0.69
    gets
    -0.69
    bots
    -0.68
    agues
    -0.68
    ourcing
    -0.67
     mandates
    -0.66
    Companies
    -0.66
    POSITIVE LOGITS
     cognitive
    0.98
     biomark
    0.96
     susceptibility
    0.95
     propensity
    0.93
     responsiveness
    0.92
     likelihood
    0.91
     retention
    0.91
     cortisol
    0.90
     metabolic
    0.90
     serum
    0.87
    Activations Density 0.092%

    No Known Activations