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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 18856
    Prev
    Next
    INDEX
    Explanations

    words related to database systems, especially focusing on the mention of the specific database "CartoDB"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific database named "CouchDB."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.86
    bourg
    -0.67
     odds
    -0.63
     Anita
    -0.62
    terday
    -0.62
    rament
    -0.62
     Hearth
    -0.61
     Kinnikuman
    -0.61
     heights
    -0.61
     Paran
    -0.60
    POSITIVE LOGITS
    DB
    1.19
    ranch
    0.95
    pedia
    0.87
    Db
    0.86
    db
    0.84
     DB
    0.79
    ynamic
    0.79
     resil
    0.78
    ERG
    0.77
    ilitation
    0.77
    Activations Density 0.011%

    No Known Activations