© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15104
    Prev
    Next
    INDEX
    Explanations

    words related to gender

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gender and related topics

    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
     GOODMAN
    -0.73
    amina
    -0.70
    BLIC
    -0.70
     Provided
    -0.68
     Warrant
    -0.68
    steen
    -0.67
     Memor
    -0.67
    iries
    -0.66
    etsk
    -0.66
    ernels
    -0.65
    POSITIVE LOGITS
     dysph
    1.02
    endered
    0.96
     genders
    0.93
     gender
    0.89
     equality
    0.89
    fuck
    0.87
    bender
    0.85
     pronouns
    0.84
     imbalance
    0.84
     stereotypes
    0.83
    Activations Density 0.016%

    No Known Activations