© 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. 1-RES-JB
    11. 9472
    Prev
    Next
    INDEX
    Explanations

    references to instances of sexual violence or assault

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.96
     Solitaire
    -0.84
    olin
    -0.76
     GOODMAN
    -0.75
    Dispatch
    -0.73
    arij
    -0.67
     Eff
    -0.65
    SourceFile
    -0.65
    VK
    -0.65
     Desk
    -0.64
    POSITIVE LOGITS
     sexually
    1.12
     assaulted
    0.97
    Sexual
    0.95
     ejac
    0.93
     raped
    0.91
     oriented
    0.90
     transmitted
    0.89
     sexual
    0.86
     genital
    0.86
     attracted
    0.83
    Activations Density 0.006%

    No Known Activations