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. 608
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web search engines

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to online search engines, particularly Google

    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
    ework
    -0.76
    EStreamFrame
    -0.76
    idis
    -0.74
    owe
    -0.73
    pered
    -0.69
    erent
    -0.68
    ewitness
    -0.68
     retreat
    -0.67
    ufact
    -0.66
    iations
    -0.64
    POSITIVE LOGITS
     queries
    1.20
     query
    1.07
     engines
    1.01
     keywords
    1.00
     results
    1.00
    results
    0.95
     engine
    0.92
    Term
    0.91
     searches
    0.91
     terms
    0.91
    Activations Density 0.063%

    No Known Activations