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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 23895
    Prev
    Next
    INDEX
    Explanations

    mentions of specific details related to cars, such as their features, production, sales, and performance

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles, specifically cars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.82
     Dull
    -0.81
     Flavoring
    -0.79
    sembly
    -0.75
    emonic
    -0.74
    xual
    -0.73
    tle
    -0.72
    edIn
    -0.72
    iversal
    -0.70
    enance
    -0.69
    POSITIVE LOGITS
    ousel
    1.41
    riages
    1.27
    penter
    1.14
    rera
    1.11
     dealership
    0.95
    riage
    0.90
    negie
    0.87
    seat
    0.84
    olina
    0.83
     parked
    0.82
    Activations Density 0.035%

    No Known Activations