Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19672
    Prev
    Next
    INDEX
    Explanations

    words related to sexual content and activity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual themes and misconduct

    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
     Bench
    -0.72
    eworks
    -0.69
    stack
    -0.68
     Dai
    -0.68
     Boom
    -0.68
    Market
    -0.68
    batch
    -0.67
    ateurs
    -0.67
    prints
    -0.66
    aez
    -0.66
    POSITIVE LOGITS
     sexual
    3.46
    Sexual
    3.09
     Sexual
    2.89
    sexual
    2.73
     sexually
    2.63
     sexuality
    2.54
     sex
    2.48
    Sex
    2.14
     homosexual
    2.06
     Sex
    2.00
    Activations Density 0.020%

    No Known Activations