© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1310
    Prev
    Next
    INDEX
    Explanations

    keywords related to gender identity and gender-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to gender in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gerr
    -0.73
     Lent
    -0.71
    Gi
    -0.70
    ernels
    -0.67
     Prosecut
    -0.66
    WT
    -0.66
     Mub
    -0.64
    BLIC
    -0.64
     Grave
    -0.64
    amina
    -0.64
    POSITIVE LOGITS
     dysph
    1.17
     equality
    1.00
     pronouns
    0.96
     Equality
    0.96
     identity
    0.90
     stereotypes
    0.89
     imbalance
    0.85
    flu
    0.85
    bending
    0.85
    bender
    0.83
    Activations Density 0.028%

    No Known Activations