© 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 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. 2-RES-JB
    11. 22374
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rape" in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "rape" in various contexts related to discussions or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uchin
    -0.84
    quickShipAvailable
    -0.82
     Solitaire
    -0.73
    avez
    -0.72
    uliffe
    -0.71
    ormons
    -0.71
    */(
    -0.70
    OTAL
    -0.69
    ocular
    -0.68
    enfranch
    -0.68
    POSITIVE LOGITS
     rape
    1.26
     Rape
    1.11
     raped
    1.07
     rapes
    1.00
    rape
    0.95
     raping
    0.93
     rapists
    0.86
    gate
    0.85
    Sexual
    0.83
    quez
    0.81
    Activations Density 0.017%

    No Known Activations