© 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. 1-RES-JB
    11. 16801
    Prev
    Next
    INDEX
    Explanations

    locations, particularly related to cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations, particularly places in Jamaica and Kingston

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itbart
    -0.88
    chen
    -0.73
    asures
    -0.71
    restrial
    -0.67
    aky
    -0.67
    iquette
    -0.65
    lling
    -0.63
    aceous
    -0.63
    tsky
    -0.62
    beit
    -0.62
    POSITIVE LOGITS
     Kingston
    1.17
     Jamaica
    1.07
     Plain
    0.95
     Jama
    0.75
    hurst
    0.74
    ilee
    0.72
     Rocks
    0.71
    ometown
    0.70
    ĵĺ
    0.69
     Mandela
    0.68
    Activations Density 0.006%

    No Known Activations