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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4204
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations, particularly counties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "county."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.94
    Quotes
    -0.70
     Pascal
    -0.65
     =>
    -0.62
    ament
    -0.62
    Rat
    -0.61
     Prometheus
    -0.60
    aments
    -0.60
     Hermes
    -0.60
     Pir
    -0.59
    POSITIVE LOGITS
     county
    3.51
     County
    2.58
     counties
    2.56
     township
    2.04
     COUNTY
    1.90
     parish
    1.77
     municipality
    1.68
     precinct
    1.68
     sheriff
    1.67
     district
    1.59
    Activations Density 0.008%

    No Known Activations