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. 18986
    Prev
    Next
    INDEX
    Explanations

    text related to computer hardware and programming

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to various topics

    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
    hement
    -0.85
     scrap
    -0.80
    xual
    -0.77
     margins
    -0.70
     diseng
    -0.70
     fou
    -0.66
     pupp
    -0.65
     writ
    -0.65
     suff
    -0.64
     adulthood
    -0.64
    POSITIVE LOGITS
    Synopsis
    0.97
    Recommended
    0.95
    inav
    0.92
    Includes
    0.88
    >>>>>>>>
    0.87
    Allows
    0.86
    ------------------------
    0.86
    Posts
    0.86
    Folder
    0.85
    Topic
    0.85
    Activations Density 0.336%

    No Known Activations