© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4-RES-JB
    11. 10719
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographic locations, particularly the city of Windsor

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Windsor and references to a specific individual named Kozinski

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

    No Comments

    Negative Logits
    ramid
    -1.08
    ynthesis
    -1.04
    undai
    -0.98
    ngth
    -0.86
    aram
    -0.82
    heres
    -0.79
    yss
    -0.79
    rity
    -0.78
    artments
    -0.78
    untu
    -0.77
    POSITIVE LOGITS
     Spit
    1.28
     Windsor
    1.05
     Castle
    0.81
     Downs
    0.80
     Township
    0.78
    forth
    0.78
    shire
    0.77
     Bram
    0.77
     Manor
    0.77
     Junction
    0.76
    Activations Density 0.016%

    No Known Activations