© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 3797
    Prev
    Next
    INDEX
    Explanations

    references to the metal "gold"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    -0.85
    ROR
    -0.85
    ————————
    -0.81
    EEE
    -0.79
    =-=-=-=-
    -0.72
    ————————————————
    -0.70
     Debor
    -0.70
    zee
    -0.69
    20439
    -0.66
    ================================================================
    -0.66
    POSITIVE LOGITS
     medal
    1.11
     coins
    1.10
     medals
    1.03
    vertisement
    1.03
     jewelry
    0.99
     gold
    0.93
     coin
    0.93
    smith
    0.89
    fish
    0.88
    coin
    0.88
    Activations Density 0.009%

    No Known Activations