Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6275
    Prev
    Next
    INDEX
    Explanations

    explicit mentions of specific body parts

    oai_token-act-pair · gpt-3.5-turbo

    words related to male and female genitalia and sexual activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.91
     GOODMAN
    -0.76
    HCR
    -0.73
    ģĸ
    -0.71
    ARY
    -0.70
    NPR
    -0.70
    ONSORED
    -0.69
    APD
    -0.68
    */(
    -0.68
    ten
    -0.67
    POSITIVE LOGITS
     penis
    1.23
     ejac
    1.20
     erection
    0.94
     enlarg
    0.91
     foreskin
    0.90
    cised
    0.86
     shaft
    0.86
     circumcised
    0.85
    WithNo
    0.84
     masturb
    0.83
    Activations Density 0.014%

    No Known Activations