© 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. 4-RES-JB
    11. 7520
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities named "Lake"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Salt Lake" and its surrounding context

    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
    binary
    -0.82
    schild
    -0.73
    ĻĤ
    -0.72
    STEM
    -0.69
    ãĤ¯
    -0.68
    ESA
    -0.67
    nostic
    -0.67
    imental
    -0.67
     streng
    -0.67
    milo
    -0.66
    POSITIVE LOGITS
    ois
    0.95
     City
    0.89
     Arabia
    0.84
     Lake
    0.82
     Ranch
    0.80
     Tribune
    0.80
     Springs
    0.78
    apolis
    0.77
    othal
    0.74
     County
    0.73
    Activations Density 0.007%

    No Known Activations