© 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 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. 0-RES-JB
    11. 13202
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual acts or assaults

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual activity and assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dhabi
    -0.74
    print
    -0.68
     Utility
    -0.68
    AI
    -0.67
    Bas
    -0.63
     Liquid
    -0.63
     Dai
    -0.63
    entry
    -0.63
    plates
    -0.63
    plate
    -0.63
    POSITIVE LOGITS
     sexually
    3.79
    Sexual
    2.33
     sexual
    2.19
    sexual
    1.97
     Sexual
    1.93
     raped
    1.88
    Sex
    1.79
     masturb
    1.70
     lewd
    1.68
     sex
    1.68
    Activations Density 0.016%

    No Known Activations