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. 1384
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mayer" and to the location "Malta."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific individuals and locations

    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
    ned
    -0.85
    kered
    -0.82
    ciples
    -0.79
    pler
    -0.79
    pling
    -0.78
    pering
    -0.75
    sell
    -0.74
    nings
    -0.73
    Ͻ
    -0.73
    ious
    -0.71
    POSITIVE LOGITS
     Mayer
    1.00
    ipop
    0.92
     Vie
    0.74
    dinand
    0.72
    FontSize
    0.72
     typ
    0.70
     Typ
    0.68
     Schmidt
    0.68
     lapse
    0.67
    irements
    0.67
    Activations Density 0.026%

    No Known Activations