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. 10-RES-JB
    6. 19750
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to successful individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     util
    -0.93
     organise
    -0.85
     Whilst
    -0.85
     whilst
    -0.83
     behaviours
    -0.82
     rumours
    -0.78
    ilst
    -0.78
     onwards
    -0.78
    alys
    -0.74
     enqu
    -0.73
    POSITIVE LOGITS
     Pulitzer
    1.11
     Nixon
    1.04
     presidents
    1.04
     Rockefeller
    1.03
     Eisenhower
    1.02
     Lyndon
    1.01
    kefeller
    0.99
     Presidents
    0.99
     Reagan
    0.99
     Watergate
    0.97
    Activations Density 1.220%

    No Known Activations