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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9702
    Prev
    Next
    INDEX
    Explanations

    locations or place names, especially related to the city of 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iatrics
    -0.83
    ãĥ¯
    -0.79
    ppo
    -0.79
    ãĥł
    -0.78
    earance
    -0.77
    ãĥĻ
    -0.77
    ersion
    -0.77
    atched
    -0.76
    ittance
    -0.76
    andem
    -0.75
    POSITIVE LOGITS
    shire
    1.02
    burg
    0.98
     Heights
    0.95
    burgh
    0.93
     Hill
    0.88
     Hills
    0.85
     Roads
    0.81
     Beach
    0.80
    yard
    0.78
     Alley
    0.77
    Activations Density 0.020%

    No Known Activations