© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10700
    Prev
    Next
    INDEX
    Explanations

    words related to the action of searching, specifically for terms related to online search engines and tools

    oai_token-act-pair · gpt-3.5-turbo

    terms related to search functionality and search engines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minecraft
    -0.76
    pered
    -0.70
    EStreamFrame
    -0.70
    iHUD
    -0.69
    cil
    -0.69
     Judith
    -0.67
    ivari
    -0.67
    Downloadha
    -0.66
    ework
    -0.65
    Death
    -0.64
    POSITIVE LOGITS
     searches
    1.00
     queries
    0.94
     keywords
    0.86
     engines
    0.84
     search
    0.84
     query
    0.81
     lookup
    0.78
     Search
    0.77
     metab
    0.75
     algorithm
    0.75
    Activations Density 0.019%

    No Known Activations