© 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. 11-RES-JB
    11. 360
    Prev
    Next
    INDEX
    Explanations

    phrases related to knee-related medical conditions and injuries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "knee" and related anatomical terms or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rans
    -0.76
    weet
    -0.75
    actionDate
    -0.73
    due
    -0.71
    KNOWN
    -0.70
    rational
    -0.69
    uno
    -0.68
    resso
    -0.67
    ource
    -0.67
    nil
    -0.65
    POSITIVE LOGITS
     jerk
    1.12
     joints
    0.96
     brace
    0.92
     pads
    0.92
     lig
    0.91
     knee
    0.89
     knees
    0.85
     bends
    0.84
     injury
    0.83
     braces
    0.82
    Activations Density 0.038%

    No Known Activations