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. 15660
    Prev
    Next
    INDEX
    Explanations

    people's names, specifically those with the name "Manuel"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Manuel" and variations of it

    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
    RFC
    -0.77
    hedral
    -0.62
    rament
    -0.61
    ewater
    -0.61
    natureconservancy
    -0.61
     favour
    -0.60
     tipping
    -0.60
    displayText
    -0.59
     mechanically
    -0.58
     shattering
    -0.58
    POSITIVE LOGITS
    phe
    1.00
    iflower
    0.99
    a
    0.95
    le
    0.94
     Castro
    0.92
    angelo
    0.87
    upe
    0.83
    oise
    0.81
     Miranda
    0.81
    zar
    0.81
    Activations Density 0.067%

    No Known Activations