Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2107
    Prev
    Next
    INDEX
    Explanations

    references to the precious 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    -0.80
    zee
    -0.77
     Consent
    -0.74
    ally
    -0.74
    ROR
    -0.74
     Stras
    -0.70
     reperto
    -0.68
     Debor
    -0.68
    mble
    -0.65
    ========
    -0.65
    POSITIVE LOGITS
    vertisement
    1.10
     medal
    1.05
     coins
    1.03
    smith
    0.98
    fish
    0.97
     jewelry
    0.92
     medals
    0.91
    stone
    0.88
    mine
    0.84
     coin
    0.83
    Activations Density 0.014%

    No Known Activations