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. 8-RES-JB
    6. 20638
    Prev
    Next
    INDEX
    Explanations

    text related to scientific research and studies

    oai_token-act-pair · gpt-3.5-turbo

    assertions or conclusions presented in studies or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     souven
    -0.91
     customary
    -0.80
     goodbye
    -0.75
     ceremonial
    -0.75
     ceremon
    -0.74
     barg
    -0.73
     sidel
    -0.72
    ascus
    -0.71
     barric
    -0.70
    icho
    -0.69
    POSITIVE LOGITS
     Specifically
    1.24
    Researchers
    1.22
    Specifically
    1.21
    Study
    1.17
    Studies
    1.14
     Researchers
    1.14
    Writing
    1.01
     Furthermore
    0.98
     Study
    0.97
    Furthermore
    0.96
    Activations Density 0.520%

    No Known Activations