© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14172
    Prev
    Next
    INDEX
    Explanations

    SQL-related terms or commands

    oai_token-act-pair · gpt-3.5-turbo

    references to SQL and related database concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Cheong
    -0.89
    HAEL
    -0.69
    free
    -0.68
     circ
    -0.68
    worn
    -0.66
    ynski
    -0.64
    flies
    -0.64
    quarters
    -0.62
    stadt
    -0.61
    length
    -0.61
    POSITIVE LOGITS
    Query
    1.01
     Server
    0.89
    ql
    0.89
    greSQL
    0.85
     query
    0.85
    query
    0.81
    ions
    0.79
     injection
    0.77
    Performance
    0.76
     Query
    0.76
    Activations Density 0.077%

    No Known Activations