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. 11-RES-JB
    6. 19530
    Prev
    Next
    INDEX
    Explanations

    government and political-related language or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant and impactful actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contents
    -1.01
    Cause
    -0.83
    Firstly
    -0.81
    ""
    -0.78
    Interstitial
    -0.77
    Reviewer
    -0.77
     haha
    -0.76
    Favorite
    -0.75
    Liter
    -0.74
     ('
    -0.74
    POSITIVE LOGITS
     policymakers
    0.91
     optimism
    0.90
     McConnell
    0.90
     Cohn
    0.89
     Boehner
    0.88
     Canaver
    0.88
     Kushner
    0.87
     Priebus
    0.87
     Republicans
    0.87
     Trump
    0.86
    Activations Density 0.603%

    No Known Activations