© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17390
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes and body shapes

    oai_token-act-pair · gpt-3.5-turbo

    references to physical anatomy and nudity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citation
    -0.83
     Mn
    -0.80
     loudspe
    -0.73
     Canaver
    -0.72
     stewards
    -0.72
     extingu
    -0.71
     procedural
    -0.70
     Sponsor
    -0.70
    externalActionCode
    -0.68
     euth
    -0.66
    POSITIVE LOGITS
     boobs
    1.91
     breasts
    1.89
     nipples
    1.76
     tits
    1.70
     panties
    1.66
     thighs
    1.58
     bikini
    1.54
     hips
    1.46
     crotch
    1.43
     nipple
    1.42
    Activations Density 0.310%

    No Known Activations