© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3628
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and sexual misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gery
    -0.79
    Luck
    -0.76
    quickShipAvailable
    -0.73
    luck
    -0.72
     Isle
    -0.69
    geries
    -0.68
    gets
    -0.67
    iton
    -0.66
     Geneva
    -0.66
    gers
    -0.65
    POSITIVE LOGITS
     assaulted
    1.36
     abused
    1.29
     harassed
    1.18
     abusing
    1.15
     assaulting
    1.14
     exploited
    1.11
     stimulated
    1.03
     suggestive
    0.98
     harassing
    0.98
     transmitted
    0.97
    Activations Density 0.039%

    No Known Activations