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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4130
    Prev
    Next
    INDEX
    Explanations

    phrases related to women or women's issues

    oai_token-act-pair · gpt-3.5-turbo

    references to women and women's issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uncle
    -0.81
    lished
    -0.80
    las
    -0.72
    odon
    -0.72
    rette
    -0.72
    uin
    -0.71
    nces
    -0.71
    hiba
    -0.70
    ills
    -0.70
    Quantity
    -0.70
    POSITIVE LOGITS
     rights
    0.96
     liberation
    0.83
     restroom
    0.82
     empowerment
    0.80
     apparel
    0.79
     Rights
    0.75
     basketball
    0.75
     Liberation
    0.74
    rights
    0.74
     clubs
    0.73
    Activations Density 0.062%

    No Known Activations