Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17903
    Prev
    Next
    INDEX
    Explanations

    SQL-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with SQL databases and queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -1.04
    angelo
    -0.69
    flies
    -0.69
     Taiwanese
    -0.68
     Byron
    -0.68
     Eliot
    -0.67
    length
    -0.66
    landish
    -0.66
     Issa
    -0.65
    piece
    -0.64
    POSITIVE LOGITS
    Query
    0.99
    greSQL
    0.97
     injection
    0.92
    ql
    0.90
     injections
    0.87
     Azure
    0.87
    SQL
    0.87
    STATE
    0.86
     databases
    0.85
    ite
    0.83
    Activations Density 0.036%

    No Known Activations