© 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. 10-RES-JB
    11. 12682
    Prev
    Next
    INDEX
    Explanations

    words related to gender, specifically focusing on women

    oai_token-act-pair · gpt-3.5-turbo

    references to women and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urers
    -0.78
    ricular
    -0.76
    uring
    -0.75
    ering
    -0.74
    ridges
    -0.73
    rete
    -0.73
    urable
    -0.69
    FontSize
    -0.67
    erman
    -0.67
    er
    -0.66
    POSITIVE LOGITS
    ici
    0.96
    SHIP
    0.93
    vironment
    0.84
    onymous
    0.84
    ico
    0.83
    CLE
    0.83
    gence
    0.81
    iak
    0.80
    icable
    0.78
    ksh
    0.78
    Activations Density 0.062%

    No Known Activations