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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4054
    Prev
    Next
    INDEX
    Explanations

    locations or references related to the state of Wisconsin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Wisconsin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     py
    -0.87
     Narc
    -0.78
     Frag
    -0.78
    phan
    -0.77
     marines
    -0.76
     Tat
    -0.76
    Cos
    -0.74
     orphans
    -0.74
     IC
    -0.72
     Malaysian
    -0.72
    POSITIVE LOGITS
     Wisconsin
    3.52
    Wisconsin
    3.47
     Milwaukee
    2.62
    waukee
    2.22
    aukee
    2.16
     WI
    2.04
     UW
    2.00
     Manit
    1.88
     Wis
    1.74
    Michigan
    1.69
    Activations Density 0.037%

    No Known Activations