© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23513
    Prev
    Next
    INDEX
    Explanations

    words related to sexual activities or sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    terms related 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dispatch
    -0.88
     Converted
    -0.76
    tower
    -0.76
    ALS
    -0.76
    GV
    -0.75
    IVERS
    -0.75
    ĪĴ
    -0.72
     Breaker
    -0.71
    live
    -0.69
     Glob
    -0.69
    POSITIVE LOGITS
     intercourse
    1.19
     assault
    1.08
    ity
    1.07
    ized
    1.06
     harassment
    1.04
    izing
    1.00
    ization
    0.98
     misconduct
    0.97
     assaults
    0.95
     arousal
    0.93
    Activations Density 0.036%

    No Known Activations