© 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. 648
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location named "Yamuna"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Yam" and related terms

    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
    enhagen
    -0.83
    hemy
    -0.70
    zzi
    -0.67
    ocalyptic
    -0.64
    byter
    -0.63
    ocene
    -0.63
    gypt
    -0.62
    instein
    -0.62
     suff
    -0.61
     Whitman
    -0.61
    POSITIVE LOGITS
    amaz
    0.98
    aji
    0.98
    amoto
    0.97
    assian
    0.91
    ahoo
    0.89
     Yam
    0.88
    azaki
    0.86
    aku
    0.84
    entary
    0.83
    borgh
    0.83
    Activations Density 0.019%

    No Known Activations