© 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. 8-RES-JB
    11. 17776
    Prev
    Next
    INDEX
    Explanations

    terms related to the location "Utica."

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or entities related to a specific place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aign
    -0.92
    egal
    -0.92
    oons
    -0.77
    staff
    -0.75
    eting
    -0.74
    entin
    -0.73
    sylvania
    -0.72
    hovah
    -0.71
    etition
    -0.71
    leaders
    -0.69
    POSITIVE LOGITS
    riks
    0.77
    gard
    0.74
     Weinstein
    0.71
    lder
    0.69
    ilitarian
    0.67
     Hills
    0.67
    ãĥŃ
    0.67
     Chapel
    0.67
     Falls
    0.64
    ILS
    0.64
    Activations Density 0.104%

    No Known Activations