© 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. 7-RES-JB
    11. 21816
    Prev
    Next
    INDEX
    Explanations

    mentions of 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angular
    -0.73
    allery
    -0.70
    rained
    -0.69
    undai
    -0.67
    opal
    -0.66
    eon
    -0.65
    gallery
    -0.65
    rices
    -0.64
    razen
    -0.64
    obyl
    -0.63
    POSITIVE LOGITS
     Rapids
    0.97
    Madison
    0.87
    Wisconsin
    0.84
    kers
    0.83
     Brewers
    0.79
     Gov
    0.79
     Springs
    0.77
     Bad
    0.74
    ites
    0.73
    manship
    0.72
    Activations Density 0.020%

    No Known Activations