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. 8-RES-JB
    6. 22170
    Prev
    Next
    INDEX
    Explanations

    mentions or references to specific events or organizations related to women's rights and activism

    oai_token-act-pair · gpt-3.5-turbo

    references to women's issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Compare
    -0.64
    quickShipAvailable
    -0.59
    GMT
    -0.55
    editor
    -0.54
     geo
    -0.54
     consolid
    -0.54
    EPA
    -0.54
     Koen
    -0.53
     mileage
    -0.52
    PN
    -0.52
    POSITIVE LOGITS
    aurus
    1.03
    ayers
    0.99
    leeve
    0.94
    atisf
    0.93
    avior
    0.93
    ourced
    0.91
    olution
    0.90
    wered
    0.88
    omew
    0.85
    plings
    0.84
    Activations Density 0.137%

    No Known Activations