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. 19566
    Prev
    Next
    INDEX
    Explanations

    computer-related keywords and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of interactive components, possibly related to gaming or software frameworks

    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
     Entered
    -0.91
     spirited
    -0.62
    hern
    -0.61
     awoken
    -0.61
    obyl
    -0.60
     Windsor
    -0.58
     Directorate
    -0.56
     Sussex
    -0.54
     Lyme
    -0.54
     heated
    -0.54
    POSITIVE LOGITS
     veter
    0.74
    retty
    0.71
    ãĥ¼ãĥĨ
    0.67
    olicy
    0.65
    çķ
    0.64
     Polk
    0.64
    ivid
    0.63
    Redd
    0.61
    paren
    0.61
    ived
    0.61
    Activations Density 1.741%

    No Known Activations