Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 11916
    Prev
    Next
    INDEX
    Explanations

    references to individuals matching a specific gender and hints at potential scenarios involving them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "woman" in various contexts

    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
    ypes
    -0.90
    ernels
    -0.79
    rament
    -0.79
    quickShipAvailable
    -0.78
    inctions
    -0.75
    raltar
    -0.74
    agascar
    -0.74
    kefeller
    -0.73
     Flavoring
    -0.73
    aucuses
    -0.73
    POSITIVE LOGITS
    izer
    1.27
    hood
    1.14
     herself
    1.01
    pher
    0.96
    folk
    0.96
    izers
    0.94
    cule
    0.89
     breastfeeding
    0.88
     vagina
    0.88
     menstru
    0.88
    Activations Density 0.061%

    No Known Activations