© 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. 4-RES-JB
    11. 20744
    Prev
    Next
    INDEX
    Explanations

    phrases related to body measurements, specifically focusing on the waist

    oai_token-act-pair · gpt-3.5-turbo

    references to body measurements and physical structures involving the waist

    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
     Appeals
    -0.71
    UE
    -0.69
     Mehran
    -0.69
    ophy
    -0.65
     PubMed
    -0.65
    actionDate
    -0.65
    audi
    -0.65
    IDA
    -0.64
    kson
    -0.64
     Greenwald
    -0.64
    POSITIVE LOGITS
    coat
    1.18
     circumference
    1.07
     waist
    1.04
    wear
    0.97
    band
    0.89
    tie
    0.89
    line
    0.87
    bands
    0.86
    worms
    0.85
    pless
    0.84
    Activations Density 0.016%

    No Known Activations