© 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. 0-RES-JB
    11. 8241
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations, specifically counties

    oai_token-act-pair · gpt-3.5-turbo

    references to specific counties

    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
    Pand
    -0.65
     norm
    -0.63
     embr
    -0.62
     titan
    -0.62
     passive
    -0.61
    sheet
    -0.61
     TIT
    -0.60
    isSpecialOrderable
    -0.59
    tracks
    -0.58
     lame
    -0.58
    POSITIVE LOGITS
     County
    3.81
     county
    2.44
     COUNTY
    2.35
     counties
    2.05
     Township
    1.90
     Parish
    1.71
     Sheriff
    1.50
     Borough
    1.45
    shire
    1.43
     Province
    1.41
    Activations Density 0.020%

    No Known Activations