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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11052
    Prev
    Next
    INDEX
    Explanations

    mentions of sexual activities or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gery
    -0.85
    quickShipAvailable
    -0.75
    gets
    -0.72
     univers
    -0.71
    batch
    -0.67
    arity
    -0.66
     beginnings
    -0.65
     realization
    -0.64
     journalism
    -0.64
    ger
    -0.64
    POSITIVE LOGITS
     assaulted
    1.13
     abused
    1.08
     harassed
    1.02
     charged
    1.01
     abusing
    0.99
     transmitted
    0.96
     exploited
    0.93
     assaulting
    0.91
     harmed
    0.88
     stimulated
    0.86
    Activations Density 0.030%

    No Known Activations