© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15882
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries, particularly wounds

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of wounds and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ructose
    -0.72
    soDeliveryDate
    -0.72
    rador
    -0.67
    essions
    -0.66
    minist
    -0.65
    role
    -0.65
    ramid
    -0.64
    racuse
    -0.64
    ullivan
    -0.64
    piracy
    -0.64
    POSITIVE LOGITS
     wounds
    1.36
     inflicted
    1.36
     healed
    1.05
     wound
    1.04
     heals
    1.01
     healing
    0.94
     heal
    0.94
     incurred
    0.90
     scars
    0.87
     wounded
    0.86
    Activations Density 0.077%

    No Known Activations