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. 10-RES-JB
    6. 24159
    Prev
    Next
    INDEX
    Explanations

    names or words related to the name "Gail" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "ail" and its variants, indicating discussions related to ailments or health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.76
    hered
    -0.70
     CES
    -0.60
     Dunham
    -0.60
    merce
    -0.58
    Karl
    -0.58
    itamin
    -0.57
    unknown
    -0.57
    ³
    -0.57
     msec
    -0.56
    POSITIVE LOGITS
    anguage
    0.93
    aments
    0.84
    ogical
    0.84
    ored
    0.82
    hog
    0.82
    aba
    0.80
    adium
    0.80
    amon
    0.80
    enge
    0.78
    iberal
    0.78
    Activations Density 0.043%

    No Known Activations