© 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. 0-RES-JB
    11. 5393
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gold"

    oai_token-act-pair · gpt-3.5-turbo

    references to gold and its various aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.72
    atile
    -0.69
     Dom
    -0.68
     Dev
    -0.67
     dev
    -0.65
     precinct
    -0.62
     Terr
    -0.61
     Ter
    -0.61
     Droid
    -0.61
     Clone
    -0.60
    POSITIVE LOGITS
    Gold
    3.12
    gold
    1.57
    Silver
    1.48
    Hold
    1.20
    ohn
    1.11
    Group
    1.08
     Goldstein
    1.07
    buy
    1.04
    Hall
    1.02
    Diamond
    1.02
    Activations Density 0.030%

    No Known Activations