© 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. 20276
    Prev
    Next
    INDEX
    Explanations

    medical terms and related words, such as medications and health conditions

    oai_token-act-pair · gpt-3.5-turbo

    significant structural or conceptual breaks in the text

    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
    sites
    -0.81
    rooms
    -0.77
    casts
    -0.72
    eworks
    -0.72
    places
    -0.72
    drops
    -0.72
    features
    -0.72
    hops
    -0.71
    steps
    -0.71
    stories
    -0.70
    POSITIVE LOGITS
     standpoint
    0.77
    ixtape
    0.69
     perspective
    0.66
     acquaintance
    0.65
     sample
    0.65
     haircut
    0.65
     prostitute
    0.65
     statement
    0.64
     variant
    0.63
     orgasm
    0.63
    Activations Density 0.841%

    No Known Activations