© 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. 16377
    Prev
    Next
    INDEX
    Explanations

    mentions/tokens of geographical locations or administrative divisions, specifically focusing on the concept of 'province'

    oai_token-act-pair · gpt-3.5-turbo

    references to provinces

    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
    pread
    -0.70
    worms
    -0.67
     MEM
    -0.66
     ATL
    -0.64
    hitting
    -0.64
     MySQL
    -0.63
     Hust
    -0.62
     leaks
    -0.61
    spin
    -0.61
    kick
    -0.61
    POSITIVE LOGITS
     province
    3.88
     Province
    3.10
     provinces
    2.72
     provincial
    2.43
     Provincial
    1.96
     municipality
    1.68
     Manitoba
    1.50
     Alberta
    1.49
     Municip
    1.45
     Ontario
    1.41
    Activations Density 0.017%

    No Known Activations