© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    6. 9667
    Prev
    Next
    INDEX
    Explanations

    mentions of circumcision, hygiene, and medical conditions related to circumcision

    oai_token-act-pair · gpt-3.5-turbo

    mentions of circumcision and 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
    WP
    -0.81
    peak
    -0.81
    hips
    -0.72
    SAY
    -0.72
    ifact
    -0.72
    ileaks
    -0.72
    Hug
    -0.70
    onde
    -0.70
    IDE
    -0.69
    igue
    -0.68
    POSITIVE LOGITS
    cision
    1.02
     circum
    1.01
     circumcision
    0.95
    scribed
    0.90
     circumcised
    0.83
    cised
    0.83
    cise
    0.77
     tubing
    0.73
    qi
    0.73
    scribe
    0.73
    Activations Density 0.018%

    No Known Activations