© 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. 11-RES-JB
    11. 22350
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or origins

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating geographical origins or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.73
    few
    -0.73
    potion
    -0.71
    tarians
    -0.68
    tops
    -0.64
    isans
    -0.63
    ographs
    -0.63
    ctor
    -0.62
    icipated
    -0.62
    EPA
    -0.61
    POSITIVE LOGITS
     afar
    1.51
     abroad
    1.12
     Latvia
    1.03
     somewhere
    1.03
     whence
    1.03
     across
    1.01
     outside
    0.99
     elsewhere
    0.99
     whom
    0.95
     Ethiopia
    0.95
    Activations Density 0.105%

    No Known Activations