© 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. 4-RES-JB
    11. 13433
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, specifically "Richmond."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Richmond

    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
    earance
    -0.78
    atched
    -0.77
    ppo
    -0.76
    atorial
    -0.76
    ittance
    -0.75
    iatrics
    -0.75
    ãĥł
    -0.73
    bsite
    -0.72
    merce
    -0.71
    agy
    -0.71
    POSITIVE LOGITS
    burgh
    1.03
    shire
    0.96
     Heights
    0.91
    burg
    0.90
     Roads
    0.85
     Hill
    0.83
     Hills
    0.80
     Alley
    0.77
    yard
    0.75
    hurst
    0.73
    Activations Density 0.007%

    No Known Activations