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. 23722
    Prev
    Next
    INDEX
    Explanations

    specific references to people, places, and organizations in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and its associations with significant political events or figures

    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
    ufact
    -0.78
    !.
    -0.78
    elaide
    -0.76
    aiden
    -0.75
    itary
    -0.75
    GH
    -0.73
    EVA
    -0.73
    pai
    -0.73
    FIELD
    -0.72
    idae
    -0.72
    POSITIVE LOGITS
     president
    1.43
     GOP
    1.39
     senator
    1.36
     Republican
    1.33
     presumptive
    1.31
     Clintons
    1.28
     congressman
    1.28
     presidential
    1.25
     RNC
    1.23
     mogul
    1.22
    Activations Density 0.363%

    No Known Activations