© 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. 2-RES-JB
    11. 17207
    Prev
    Next
    INDEX
    Explanations

    mentions of the medical condition "concussion"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concussions and head injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.76
    ynt
    -0.68
    Export
    -0.67
    upt
    -0.64
    bor
    -0.62
    Keefe
    -0.62
    FORE
    -0.62
    NT
    -0.61
    outh
    -0.61
    agy
    -0.61
    POSITIVE LOGITS
     concussion
    1.10
    ussions
    0.91
    ussion
    0.90
    querque
    0.76
    ilage
    0.74
    buster
    0.73
     Injury
    0.73
     grenades
    0.73
    wcs
    0.71
    olicy
    0.69
    Activations Density 0.009%

    No Known Activations