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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 13933
    Prev
    Next
    INDEX
    Explanations

    descriptions related to coins and minting processes

    oai_token-act-pair · gpt-3.5-turbo

    references to coins and their characteristics

    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
    yip
    -0.88
    Lear
    -0.83
     robots
    -0.82
    Uber
    -0.78
    odcast
    -0.78
    onomous
    -0.78
    rawdownloadcloneembedreportprint
    -0.78
    plugins
    -0.77
    Coun
    -0.76
     robotics
    -0.76
    POSITIVE LOGITS
    intage
    1.14
     mint
    1.08
     Mint
    1.06
     sterling
    1.05
     matte
    1.04
     vintage
    1.00
     collector
    0.98
     nickel
    0.97
     engraved
    0.96
     Vintage
    0.95
    Activations Density 0.393%

    No Known Activations