© 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. 7-RES-JB
    11. 13086
    Prev
    Next
    INDEX
    Explanations

    SQL-related terms and queries

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to SQL and database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.90
     Eliot
    -0.73
    flies
    -0.71
    enberg
    -0.69
     Taiwanese
    -0.66
     Carly
    -0.62
     Nev
    -0.62
     Dru
    -0.62
    verett
    -0.62
     Frem
    -0.62
    POSITIVE LOGITS
    greSQL
    1.04
    ite
    0.98
    Query
    0.97
     injection
    0.91
    ql
    0.91
     Server
    0.91
     injections
    0.85
     Database
    0.84
    Connection
    0.83
     Azure
    0.83
    Activations Density 0.061%

    No Known Activations