Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13342
    Prev
    Next
    INDEX
    Explanations

    words related to sexual activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and misconduct

    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
    IVERS
    -0.83
     Glob
    -0.76
     Converted
    -0.74
    olin
    -0.72
    oday
    -0.69
    Dispatch
    -0.68
     Breaker
    -0.68
    bley
    -0.67
    ernels
    -0.64
    live
    -0.64
    POSITIVE LOGITS
     assault
    1.34
     harassment
    1.27
     assaults
    1.19
     misconduct
    1.18
     intercourse
    1.14
     abuse
    1.10
     exploitation
    1.07
    ized
    1.03
     harass
    0.98
     coercion
    0.98
    Activations Density 0.028%

    No Known Activations