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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8043
    Prev
    Next
    INDEX
    Explanations

    references to websites and social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship and attribution in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.59
    gui
    -0.57
    pex
    -0.56
    gew
    -0.55
    phas
    -0.54
    iage
    -0.53
    stood
    -0.53
    Args
    -0.53
    stones
    -0.52
    lication
    -0.52
    POSITIVE LOGITS
     subscribe
    0.77
    Subscribe
    0.77
     newsletter
    0.76
     HuffPost
    0.76
    iframe
    0.74
     Email
    0.74
     Subscribe
    0.73
     Newsletter
    0.72
     embed
    0.72
     Huffington
    0.71
    Activations Density 0.987%

    No Known Activations