© 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. 2370
    Prev
    Next
    INDEX
    Explanations

    body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and their locations on the body

    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
    DragonMagazine
    -0.83
    ezvous
    -0.78
     guiActiveUn
    -0.73
    ILE
    -0.71
     Dealer
    -0.69
    endiary
    -0.69
     Depot
    -0.68
    arcity
    -0.68
    osate
    -0.68
    irable
    -0.67
    POSITIVE LOGITS
     ears
    1.74
     shoulders
    1.69
     lungs
    1.69
     thighs
    1.67
     legs
    1.65
     ankles
    1.63
     wrists
    1.62
     lips
    1.62
     knees
    1.62
     toes
    1.61
    Activations Density 0.144%

    No Known Activations