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. 11-RES-JB
    6. 19408
    Prev
    Next
    INDEX
    Explanations

    cities combined with the suffix "isco"

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anship
    -0.71
    arks
    -0.59
     promot
    -0.51
     CrossRef
    -0.50
    rals
    -0.48
    laus
    -0.48
    Route
    -0.47
    parser
    -0.47
    cache
    -0.45
     recru
    -0.45
    POSITIVE LOGITS
    illy
    0.58
    Ħ¢
    0.57
    mond
    0.54
    Į
    0.52
    note
    0.52
    stown
    0.50
    ointment
    0.50
    ouple
    0.49
    ridge
    0.48
    ebook
    0.48
    Activations Density 0.268%

    No Known Activations