© 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. 0-RES-JB
    11. 14991
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Gold."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Gold" in various contexts

    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
    ONT
    -0.79
    uncture
    -0.75
     stru
    -0.74
     indu
    -0.71
     condem
    -0.70
    à¦
    -0.70
    oper
    -0.69
     disse
    -0.68
    ressor
    -0.67
     passers
    -0.67
    POSITIVE LOGITS
     Gold
    3.79
    Gold
    2.83
     gold
    2.38
    gold
    2.24
     GOLD
    2.09
     Silver
    1.89
     Bronze
    1.85
     Platinum
    1.80
    Silver
    1.67
     Diamond
    1.58
    Activations Density 0.013%

    No Known Activations