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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 20853
    Prev
    Next
    INDEX
    Explanations

    articles with specific code-like characters likely indicating a beginning and/or ending of a section or paragraph

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of high-stakes situations or events related to crises and emergencies

    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
     Tsukuyomi
    -0.86
     sucker
    -0.75
     ranged
    -0.75
     course
    -0.74
     boxed
    -0.74
     synerg
    -0.73
     ourselves
    -0.73
     correl
    -0.73
     myself
    -0.72
     nuts
    -0.71
    POSITIVE LOGITS
    Updated
    1.92
    Posted
    1.82
    hello
    1.81
    Enlarge
    1.78
    Published
    1.72
    WASHINGTON
    1.65
    By
    1.64
    SAN
    1.54
    toggle
    1.54
    CLOSE
    1.47
    Activations Density 0.197%

    No Known Activations