© 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. 10-RES-JB
    11. 14133
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and related terminology

    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
    luck
    -0.79
    gery
    -0.78
     horizont
    -0.76
    gets
    -0.76
    orem
    -0.76
     Worlds
    -0.70
    Luck
    -0.69
     univers
    -0.68
     theorem
    -0.68
    gers
    -0.67
    POSITIVE LOGITS
     assaulted
    1.19
     abused
    1.13
     abusing
    1.10
     assaulting
    1.09
     harassed
    1.06
     charged
    1.03
     harassing
    0.97
     stimulated
    0.97
     exploited
    0.94
     transmitted
    0.92
    Activations Density 0.042%

    No Known Activations