© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18241
    Prev
    Next
    INDEX
    Explanations

    references to specific body parts, like 'waist' and 'crotch'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to body parts, particularly those in the lower torso region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PubMed
    -0.77
    IDA
    -0.70
     Suc
    -0.68
    audi
    -0.66
    vernment
    -0.65
     Appeals
    -0.65
    Downloadha
    -0.62
    ertodd
    -0.62
    actionDate
    -0.61
     Regulatory
    -0.60
    POSITIVE LOGITS
     circumference
    1.19
     waist
    1.12
    coat
    1.06
    tie
    0.93
     strap
    0.92
    wear
    0.92
     neck
    0.90
    belt
    0.88
    bone
    0.85
    bridge
    0.82
    Activations Density 0.004%

    No Known Activations