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. 7-RES-JB
    6. 10225
    Prev
    Next
    INDEX
    Explanations

    words related to sexual misconduct

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AY
    -0.72
     breaker
    -0.72
    IVERS
    -0.70
    REC
    -0.70
    SAY
    -0.66
     evapor
    -0.65
    alg
    -0.65
    repair
    -0.65
    english
    -0.65
     tune
    -0.64
    POSITIVE LOGITS
     inappropriately
    0.98
     sexually
    0.97
     grop
    0.94
     grooming
    0.94
    usky
    0.92
    Sexual
    0.89
     prostitutes
    0.85
     mol
    0.84
     sexual
    0.83
    ophile
    0.82
    Activations Density 0.158%

    No Known Activations