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. 0-RES-JB
    6. 21561
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Eskimo" or variations of the word

    oai_token-act-pair · gpt-3.5-turbo

    references to the Edmonton Eskimos and related organizations or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taker
    -0.75
    hyde
    -0.73
    utter
    -0.73
    idge
    -0.71
    itter
    -0.69
     Polk
    -0.67
     VMware
    -0.67
    oldemort
    -0.67
    626
    -0.66
    eston
    -0.66
    POSITIVE LOGITS
     Bom
    3.18
     Esk
    1.74
    BN
    1.57
     Ess
    1.50
     CFL
    1.28
     Sapp
    1.24
     Arg
    1.24
     Bok
    1.21
     Bowman
    1.20
     Dock
    1.18
    Activations Density 0.056%

    No Known Activations