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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 23926
    Prev
    Next
    INDEX
    Explanations

    references to sexual activity or abuse

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.93
     GOODMAN
    -0.85
    Dispatch
    -0.78
    olin
    -0.74
    WARD
    -0.71
    eer
    -0.69
    IELD
    -0.68
     Solitaire
    -0.66
    VL
    -0.66
     Maduro
    -0.65
    POSITIVE LOGITS
     assaulted
    0.93
     sexually
    0.89
     attracted
    0.85
     oriented
    0.84
     transmitted
    0.84
     harassed
    0.82
     assaulting
    0.82
    Sexual
    0.81
     raped
    0.80
     intercourse
    0.80
    Activations Density 0.007%

    No Known Activations