© 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. 10-RES-JB
    11. 5398
    Prev
    Next
    INDEX
    Explanations

    mentions of sewing, drawing, writing, carving, or etching on various surfaces

    oai_token-act-pair · gpt-3.5-turbo

    actions related to sewing and crafting

    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
    Reviewer
    -0.85
    EStreamFrame
    -0.76
    assetsadobe
    -0.73
     facult
    -0.70
    Availability
    -0.66
    kj
    -0.66
     htt
    -0.65
     Provided
    -0.62
    bringing
    -0.61
    gd
    -0.61
    POSITIVE LOGITS
     onto
    1.20
     initials
    1.11
     swast
    1.05
     nails
    1.04
     markings
    1.03
     graffiti
    0.98
     portraits
    0.91
     etched
    0.89
     holes
    0.89
     symbols
    0.88
    Activations Density 0.133%

    No Known Activations