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. 549
    Prev
    Next
    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics related to serious societal issues

    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
     favorably
    -1.06
     favor
    -0.99
     favored
    -0.93
     honors
    -0.90
     subsidized
    -0.89
     favoring
    -0.88
     favors
    -0.87
     willfully
    -0.85
     caliber
    -0.84
     flavors
    -0.83
    POSITIVE LOGITS
    However
    1.60
    Labour
    1.57
    Speaking
    1.54
    Scotland
    1.49
    BBC
    1.48
    Shape
    1.43
    Scroll
    1.43
    Mr
    1.41
    Professor
    1.41
    Writing
    1.41
    Activations Density 0.414%

    No Known Activations