© 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. 3-RES-JB
    11. 721
    Prev
    Next
    INDEX
    Explanations

    SQL-related terms or queries

    oai_token-act-pair · gpt-3.5-turbo

    references to SQL (Structured Query Language) and its usage

    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
     Cheong
    -0.94
    flies
    -0.73
     Taiwanese
    -0.71
    joy
    -0.70
     Roc
    -0.68
    giving
    -0.66
    kos
    -0.65
     Byron
    -0.64
     circ
    -0.64
    landish
    -0.62
    POSITIVE LOGITS
    Query
    1.01
     Azure
    0.93
     SQL
    0.93
     injection
    0.93
     sql
    0.92
    omnia
    0.91
     Server
    0.90
    SQL
    0.90
    STATE
    0.89
    ite
    0.86
    Activations Density 0.008%

    No Known Activations