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. 11314
    Prev
    Next
    INDEX
    Explanations

    updates and changes in software or systems

    oai_token-act-pair · gpt-3.5-turbo

    elements related to software updates and changes

    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
     eleph
    -0.80
     stereotyp
    -0.76
     pictured
    -0.74
     photographed
    -0.72
    orkshire
    -0.72
    llah
    -0.71
     hors
    -0.70
     imperson
    -0.69
     Beir
    -0.69
     dressed
    -0.69
    POSITIVE LOGITS
    Version
    1.04
    Patch
    0.95
     Fixes
    0.94
    Developer
    0.92
    Changes
    0.91
    Added
    0.87
     Revised
    0.87
    FIX
    0.87
    iOS
    0.87
    Updated
    0.85
    Activations Density 0.408%

    No Known Activations