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. 9-RES-JB
    6. 11498
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics related to different topics or events

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horm
    -0.87
     sizing
    -0.75
     welf
    -0.70
     compan
    -0.62
     reluctantly
    -0.61
     testim
    -0.61
    soDeliveryDate
    -0.61
     embr
    -0.59
     hindsight
    -0.59
     headlights
    -0.58
    POSITIVE LOGITS
     354
    0.95
     387
    0.93
     296
    0.91
     318
    0.90
     378
    0.90
     286
    0.89
     322
    0.89
     389
    0.89
     337
    0.88
     294
    0.88
    Activations Density 0.605%

    No Known Activations