© 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. 7-RES-JB
    11. 13386
    Prev
    Next
    INDEX
    Explanations

    words related to a particular geographical location or entity, specifically "New England."

    oai_token-act-pair · gpt-3.5-turbo

    references to New England

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.88
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    NetMessage
    -0.73
    ngth
    -0.71
    =-=-=-=-
    -0.70
    ongyang
    -0.70
    zers
    -0.69
    vana
    -0.69
     Mehran
    -0.69
    chio
    -0.69
    POSITIVE LOGITS
     Patriots
    0.98
    ers
    0.93
     Armory
    0.78
     Revolution
    0.77
     Journal
    0.75
     Gazette
    0.73
     Conserv
    0.72
     Telecommunications
    0.69
    er
    0.68
     Meadow
    0.68
    Activations Density 0.029%

    No Known Activations