© 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. 1-RES-JB
    11. 15823
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions or injuries, specifically focusing on ACL tears

    oai_token-act-pair · gpt-3.5-turbo

    references to ligaments, particularly the ACL, and instances of injury related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Riding
    -0.73
     Worldwide
    -0.71
     Planning
    -0.68
    DEM
    -0.67
     Teach
    -0.67
     Median
    -0.66
     Presidential
    -0.66
     Consumer
    -0.66
     McKin
    -0.65
    Discussion
    -0.65
    POSITIVE LOGITS
     lig
    1.31
    atures
    1.01
    ature
    0.98
     agre
    0.94
     acids
    0.94
     arrang
    0.92
     describ
    0.91
    aments
    0.90
     elbows
    0.90
     corrid
    0.90
    Activations Density 0.005%

    No Known Activations