© 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. 3-RES-JB
    11. 9735
    Prev
    Next
    INDEX
    Explanations

    words related to gender and gender identity

    oai_token-act-pair · gpt-3.5-turbo

    words related to gender identity and transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quantity
    -0.67
     Wolves
    -0.64
    akening
    -0.63
     approximate
    -0.62
     Naples
    -0.61
     majority
    -0.60
    umm
    -0.60
     quantities
    -0.60
     Burlington
    -0.60
     Mehran
    -0.60
    POSITIVE LOGITS
    lich
    1.01
    mint
    0.95
    xual
    0.92
    backer
    0.89
    grass
    0.82
    stellar
    0.77
     este
    0.76
    knife
    0.74
    lein
    0.74
    mort
    0.73
    Activations Density 0.012%

    No Known Activations