Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 928
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic regions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical regions

    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
    ricks
    -0.85
     Turing
    -0.72
     Clicker
    -0.70
    busters
    -0.67
    bats
    -0.67
    Ly
    -0.66
     Answers
    -0.65
    quickShipAvailable
    -0.64
    icy
    -0.63
    âĢ¢âĢ¢
    -0.62
    POSITIVE LOGITS
     region
    3.65
     Region
    2.53
    region
    2.49
     regions
    2.37
    Region
    2.11
     area
    1.90
     Regions
    1.79
     regional
    1.75
     province
    1.72
     peninsula
    1.71
    Activations Density 0.016%

    No Known Activations