© 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. 4-RES-JB
    11. 10306
    Prev
    Next
    INDEX
    Explanations

    references to the state of Hawaii, including locations, events, and people associated with Hawaii

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hawaii

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

    No Comments

    Negative Logits
    byn
    -0.98
    chel
    -0.82
    ror
    -0.78
    uers
    -0.76
    rations
    -0.76
    bol
    -0.73
    urgical
    -0.72
    ocrats
    -0.72
     Notting
    -0.70
    parts
    -0.69
    POSITIVE LOGITS
    aii
    1.14
     Islands
    1.00
     Hawai
    0.97
     Hawaii
    0.95
     Honolulu
    0.92
     Hawaiian
    0.89
     Airlines
    0.88
    awei
    0.79
    Haw
    0.78
     Strait
    0.77
    Activations Density 0.012%

    No Known Activations