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. 4961
    Prev
    Next
    INDEX
    Explanations

    book titles or major publication titles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to food or recipes

    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
    ynt
    -0.60
     radar
    -0.59
     nuisance
    -0.55
    nikov
    -0.54
     bleed
    -0.53
     bre
    -0.52
    ittal
    -0.52
     ratt
    -0.52
     hyd
    -0.51
     bl
    -0.51
    POSITIVE LOGITS
    ONSORED
    0.78
    Reviewed
    0.75
    Interstitial
    0.69
    ================================================================
    0.69
     Cosponsors
    0.68
    Present
    0.66
     Edition
    0.65
     Retrieved
    0.62
    Adapt
    0.61
    _.
    0.61
    Activations Density 0.988%

    No Known Activations