© 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. 11-RES-JB
    11. 2399
    Prev
    Next
    INDEX
    Explanations

    strong and influential female characters

    oai_token-act-pair · gpt-3.5-turbo

    references to strong female characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Female Descriptors

    No Comments

    Negative Logits
    Report
    -0.85
    osate
    -0.82
    ulic
    -0.81
    displayText
    -0.75
    inventoryQuantity
    -0.73
    Atlantic
    -0.72
    ache
    -0.72
    ickets
    -0.71
     brakes
    -0.71
    sterdam
    -0.69
    POSITIVE LOGITS
     characters
    2.06
     Characters
    1.83
     protagonists
    1.79
     protagonist
    1.74
     character
    1.73
     villains
    1.73
     trope
    1.62
     villain
    1.60
     tropes
    1.59
    Characters
    1.55
    Activations Density 0.613%

    No Known Activations