© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic regions or areas

    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
    vous
    -0.79
    forestation
    -0.79
    ificial
    -0.78
    offer
    -0.78
    ongyang
    -0.74
    thood
    -0.73
    actionDate
    -0.72
    IGHTS
    -0.72
    enstein
    -0.72
    uments
    -0.71
    POSITIVE LOGITS
     Postal
    0.82
     Regional
    0.80
     Railroad
    0.80
     Rapid
    0.79
     newspapers
    0.79
     Peninsula
    0.79
     Territories
    0.78
     suburbs
    0.77
     region
    0.77
     diner
    0.76
    Activations Density 0.043%

    No Known Activations