© 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. 1-RES-JB
    11. 21559
    Prev
    Next
    INDEX
    Explanations

    female-related references

    oai_token-act-pair · gpt-3.5-turbo

    gender-specific references, particularly to females

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horm
    -0.74
     tremend
    -0.73
     speculate
    -0.71
     worsen
    -0.68
     reservation
    -0.67
     assume
    -0.67
     conduc
    -0.64
     misunder
    -0.63
     reconc
    -0.63
     seiz
    -0.62
    POSITIVE LOGITS
    misc
    0.81
    pressed
    0.77
    cial
    0.75
    PRESS
    0.72
    lde
    0.70
    naissance
    0.70
    ful
    0.70
    mph
    0.68
    HER
    0.68
    knife
    0.67
    Activations Density 0.000%

    No Known Activations