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. 4018
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of women

    oai_token-act-pair · gpt-3.5-turbo

    references to women

    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
     retri
    -0.76
     addon
    -0.70
    leon
    -0.68
    azes
    -0.67
     sprite
    -0.65
     Takeru
    -0.64
     awoken
    -0.64
     infect
    -0.64
     flipping
    -0.63
     emitting
    -0.62
    POSITIVE LOGITS
     Women
    3.65
    Women
    3.31
    women
    2.54
     women
    2.43
     Woman
    2.36
     WOM
    2.32
     Ladies
    2.08
     Female
    1.90
     Girls
    1.90
    Woman
    1.88
    Activations Density 0.013%

    No Known Activations