© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20226
    Prev
    Next
    INDEX
    Explanations

    references to the Google search engine and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to search engines, specifically Google

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pered
    -0.82
    ework
    -0.81
    roach
    -0.69
    ameron
    -0.68
     retreat
    -0.67
    enei
    -0.65
     warm
    -0.65
    iations
    -0.63
    adra
    -0.62
     ceremonial
    -0.62
    POSITIVE LOGITS
     queries
    1.04
     keywords
    0.97
     query
    0.95
     searches
    0.91
     metab
    0.90
     lookup
    0.88
     sear
    0.88
    results
    0.83
     keyword
    0.82
    Search
    0.81
    Activations Density 0.065%

    No Known Activations