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. 10-RES-JB
    6. 19305
    Prev
    Next
    INDEX
    Explanations

    phrases related to allegations of sexual harassment or misconduct

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual harassment and misconduct allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.88
     export
    -0.82
    rador
    -0.80
     conserve
    -0.77
    iris
    -0.77
     ration
    -0.77
    export
    -0.76
    merga
    -0.75
    ignty
    -0.74
    natureconservancy
    -0.74
    POSITIVE LOGITS
     Weinstein
    1.50
     accuser
    1.47
     accus
    1.42
     sexual
    1.42
     grop
    1.41
     allegations
    1.41
    Sexual
    1.39
     sexually
    1.38
     Cosby
    1.35
     lewd
    1.25
    Activations Density 0.481%

    No Known Activations