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. 13469
    Prev
    Next
    INDEX
    Explanations

    names along with their job titles

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to political figures and institutions

    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
    $.
    -0.64
     undet
    -0.61
     detriment
    -0.58
    ]."
    -0.56
    ".[
    -0.55
    EStreamFrame
    -0.54
     therein
    -0.53
    ãģĻ
    -0.52
     vulner
    -0.52
    ").
    -0.52
    POSITIVE LOGITS
     meanwhile
    0.97
     echoed
    0.77
     reacted
    0.70
     congratulated
    0.64
     commented
    0.63
     spokesman
    0.62
     welcomed
    0.62
     applauded
    0.62
     countered
    0.62
     responded
    0.61
    Activations Density 1.179%

    No Known Activations