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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 8315
    Prev
    Next
    INDEX
    Explanations

    database-related terms and operations in text, particularly focusing on the word "query"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "query" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proud
    -0.71
    Circ
    -0.71
    belt
    -0.69
     Lump
    -0.68
    rated
    -0.68
     Angela
    -0.66
    pires
    -0.65
     Mold
    -0.65
     Camp
    -0.65
    roud
    -0.64
    POSITIVE LOGITS
     query
    3.46
     queries
    3.15
    query
    2.39
    Query
    2.30
     Query
    2.29
     quer
    2.08
    SQL
    1.41
    QL
    1.30
     enqu
    1.29
     SQL
    1.25
    Activations Density 0.010%

    No Known Activations