© 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. 20268
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and treatments specifically involving the femur bone

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "fem" in various contexts related to gender and physical traits

    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
     Gott
    -0.75
    OUGH
    -0.72
    VW
    -0.68
     Oaks
    -0.66
     Pyramid
    -0.66
     Grateful
    -0.65
    aldehyde
    -0.64
    rawdownloadcloneembedreportprint
    -0.63
     Button
    -0.61
    upon
    -0.61
    POSITIVE LOGITS
     fem
    1.26
    puter
    1.06
     princ
    0.99
     Fem
    0.92
    icides
    0.87
    ldom
    0.86
     trave
    0.83
    icide
    0.83
    galitarian
    0.82
    heter
    0.81
    Activations Density 0.010%

    No Known Activations