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. 3-RES-JB
    6. 11584
    Prev
    Next
    INDEX
    Explanations

    patterns in the data that are not directly related to a specific concept or topic

    oai_token-act-pair · gpt-3.5-turbo

    passive constructions and actions related to questioning or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swe
    -0.62
     hust
    -0.62
     lifes
    -0.60
     commission
    -0.59
     axe
    -0.59
     ever
    -0.59
     creature
    -0.58
     appe
    -0.58
     seeking
    -0.58
     scrap
    -0.58
    POSITIVE LOGITS
    Advertisement
    1.09
    Advertisements
    1.03
    ccording
    1.00
    Conclusion
    0.99
    Meanwhile
    0.98
    Recommended
    0.97
    Also
    0.97
    If
    0.97
    Anonymous
    0.96
    However
    0.95
    Activations Density 1.273%

    No Known Activations