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. 13803
    Prev
    Next
    INDEX
    Explanations

    instances where the text describes a difficult or challenging situation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of" indicating notable examples or categories

    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
    culosis
    -0.72
     IPM
    -0.66
    anse
    -0.64
     agre
    -0.62
    lean
    -0.61
    iture
    -0.60
    ertodd
    -0.59
     diagram
    -0.59
     disposed
    -0.58
     onwards
    -0.58
    POSITIVE LOGITS
    arching
    0.78
    icial
    0.77
    ãĤ¨
    0.69
    sted
    0.67
    sson
    0.64
     sorts
    0.64
    dden
    0.60
    ounding
    0.58
    itol
    0.57
    iciary
    0.56
    Activations Density 0.060%

    No Known Activations