© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 1959
    Prev
    Next
    INDEX
    Explanations

    references to incidents of sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sexual assault or rape

    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
    -0.97
    uchin
    -0.83
    avez
    -0.80
    alach
    -0.76
     magnification
    -0.73
    bid
    -0.72
    ighty
    -0.72
     gust
    -0.71
    issues
    -0.71
    alg
    -0.71
    POSITIVE LOGITS
     raped
    1.26
     raping
    1.20
     rape
    1.12
     rapes
    0.95
     rapists
    0.93
     Rape
    0.92
     TAMADRA
    0.83
    ocide
    0.82
    quez
    0.82
     rapist
    0.81
    Activations Density 0.014%

    No Known Activations