© 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. 6-RES-JB
    11. 12868
    Prev
    Next
    INDEX
    Explanations

    the term "Pacific" followed by a specific word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Pacific region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perse
    -0.89
    mble
    -0.80
    ded
    -0.80
    CLE
    -0.79
    gel
    -0.76
    Downloadha
    -0.76
    chel
    -0.75
    FUL
    -0.75
    poke
    -0.74
    ALTH
    -0.73
    POSITIVE LOGITS
     Rim
    1.30
     Ocean
    1.17
     Northwest
    1.13
     Pacific
    1.03
     Coast
    1.02
     Islands
    0.95
     Highlands
    0.91
     Crest
    0.89
     Island
    0.88
     Airlines
    0.88
    Activations Density 0.013%

    No Known Activations