© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    words related to body parts, specifically focusing on legs and feet

    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
    ISM
    -0.68
    eers
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    District
    -0.66
    Leader
    -0.65
    RY
    -0.65
     Ethics
    -0.65
    ivals
    -0.64
    âĸ¬
    -0.63
    Offline
    -0.61
    POSITIVE LOGITS
    pring
    1.28
    cape
    1.23
    peed
    1.20
    pan
    1.20
    mith
    1.19
    creen
    1.17
     protr
    1.16
    pots
    1.11
    uits
    1.10
    pread
    1.08
    Activations Density 0.199%

    No Known Activations