© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10078
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions involving teeth or jaws

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "bite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AMP
    -0.74
     Depot
    -0.73
    ourced
    -0.73
    oppable
    -0.73
    Export
    -0.69
    ocally
    -0.69
     Fargo
    -0.69
    otions
    -0.69
    YL
    -0.66
    unda
    -0.65
    POSITIVE LOGITS
     bite
    1.09
     bitten
    1.03
    bite
    0.97
     gum
    0.90
     bites
    0.89
     bait
    0.87
     nails
    0.87
    thro
    0.84
     biting
    0.83
    hered
    0.81
    Activations Density 0.037%

    No Known Activations