© 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. 4-RES-JB
    11. 4834
    Prev
    Next
    INDEX
    Explanations

    references to physical bodies or body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to bodies and body-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilee
    -0.71
    à¼
    -0.71
    zai
    -0.68
    Pacific
    -0.67
    STAR
    -0.65
    schild
    -0.64
     Kingdoms
    -0.64
    Å¡
    -0.63
    Writer
    -0.63
    NL
    -0.63
    POSITIVE LOGITS
    atures
    0.68
     Bones
    0.67
     slic
    0.67
     freezer
    0.62
     resemblance
    0.61
    nutrition
    0.61
    gio
    0.61
    edly
    0.61
     odor
    0.60
    nsics
    0.60
    Activations Density 0.139%

    No Known Activations