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. 4454
    Prev
    Next
    INDEX
    Explanations

    mentions of "Kentucky" and "Mitch McConnell"

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent political figures and their party affiliations

    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
     SAP
    -0.98
     Sanchez
    -0.97
     Aad
    -0.96
     Icelandic
    -0.96
    Ice
    -0.91
     iceberg
    -0.91
     hier
    -0.90
    æ
    -0.90
     Iceland
    -0.89
    ijk
    -0.88
    POSITIVE LOGITS
     Kentucky
    2.36
     Louisville
    2.23
    Kent
    1.99
     Lexington
    1.97
     KY
    1.94
     McConnell
    1.78
    KY
    1.73
     Ky
    1.71
    Ky
    1.70
    Louis
    1.42
    Activations Density 0.161%

    No Known Activations