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. 1-RES-JB
    6. 8382
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to countries or regions, particularly El Salvador

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the prefix "El" followed by a noun, likely indicating locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.87
    hire
    -0.84
     Pict
    -0.78
    SourceFile
    -0.72
    )=(
    -0.71
    henko
    -0.71
     Anthem
    -0.70
     NZ
    -0.68
    NOW
    -0.68
     Doct
    -0.66
    POSITIVE LOGITS
    azer
    0.98
    igible
    0.97
     Niño
    0.91
    ving
    0.90
    iza
    0.85
    itability
    0.85
    azy
    0.84
    bert
    0.84
     Salvador
    0.84
    bows
    0.83
    Activations Density 0.012%

    No Known Activations