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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9934
    Prev
    Next
    INDEX
    Explanations

    information related to physical injuries and medical conditions, especially those involving cuts, bruises, swelling, and specific body parts

    oai_token-act-pair · gpt-3.5-turbo

    details about injuries and physical trauma

    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
    Reply
    -0.76
    iculture
    -0.75
     refinery
    -0.64
    Catalog
    -0.64
    Daily
    -0.64
     Daylight
    -0.63
     kW
    -0.62
    MSN
    -0.62
    Ware
    -0.60
    Weather
    -0.60
    POSITIVE LOGITS
     cheeks
    1.42
     thighs
    1.37
     legs
    1.28
     breasts
    1.28
     genitals
    1.27
     buttocks
    1.27
     abdomen
    1.26
     hips
    1.25
     ankles
    1.24
     ears
    1.23
    Activations Density 0.272%

    No Known Activations