Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 605
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending in punctuation

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that convey emphasis or significance

    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
     artisan
    -0.73
     trade
    -0.72
     apprentice
    -0.66
    omics
    -0.66
     explor
    -0.65
     elbow
    -0.65
     wound
    -0.64
     freshwater
    -0.63
    kefeller
    -0.63
    emaker
    -0.63
    POSITIVE LOGITS
     Especially
    1.02
     However
    0.98
     Referred
    0.95
     Apparently
    0.92
     Though
    0.92
     Additionally
    0.92
     Hence
    0.92
     Also
    0.91
     They
    0.91
     According
    0.91
    Activations Density 0.448%

    No Known Activations