© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 13562
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "largest" followed by a numeric value, which indicates a superlative description of size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    superlative terms indicating the largest entities in various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    facing
    -0.82
    anship
    -0.77
    docs
    -0.77
    instead
    -0.77
    fy
    -0.72
    love
    -0.70
    tell
    -0.70
    Dialogue
    -0.69
    PORT
    -0.69
    nikov
    -0.69
    POSITIVE LOGITS
     shareholder
    1.04
     employer
    0.94
     seller
    0.94
     proponent
    0.92
     purchaser
    0.92
     contributor
    0.91
     single
    0.89
     creditor
    0.89
     ever
    0.88
     bidder
    0.86
    Activations Density 0.046%

    No Known Activations