© 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. 10-RES-JB
    11. 12044
    Prev
    Next
    INDEX
    Explanations

    mentions of specific body parts being injured

    oai_token-act-pair · gpt-3.5-turbo
    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
     Authors
    -0.69
     invitations
    -0.63
     discounts
    -0.61
     Administ
    -0.61
     constraints
    -0.60
     lobbyists
    -0.60
    TPP
    -0.59
    TIME
    -0.59
    DragonMagazine
    -0.56
     tides
    -0.55
    POSITIVE LOGITS
     stride
    1.04
     abdomen
    1.04
     front
    1.01
     retaliation
    0.96
     cheek
    0.96
     thigh
    0.94
     chest
    0.90
     forehead
    0.90
    arms
    0.88
     extrem
    0.87
    Activations Density 0.053%

    No Known Activations