© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3394
    Prev
    Next
    INDEX
    Explanations

    keywords related to regions in the United States, especially focusing on the Midwest

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical regions, particularly the Midwest and Midlands

    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
    thood
    -0.90
    rators
    -0.81
    ration
    -0.75
    rations
    -0.74
    vel
    -0.74
    pert
    -0.73
    rings
    -0.71
    acl
    -0.71
    ificial
    -0.70
    aders
    -0.70
    POSITIVE LOGITS
     Midwest
    1.35
     Northeast
    0.98
     Mayhem
    0.88
     Regional
    0.82
     Rapids
    0.80
    adelphia
    0.80
     Region
    0.79
     Southwest
    0.76
     Midlands
    0.76
     Plains
    0.76
    Activations Density 0.008%

    No Known Activations