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. 2-RES-JB
    6. 16194
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements or emphatic quotes

    oai_token-act-pair · gpt-3.5-turbo

    exclamation and question punctuation, particularly in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eds
    -0.70
    ©¶æ
    -0.69
    mber
    -0.61
    Ĥª
    -0.61
    EStreamFrame
    -0.60
    gaard
    -0.59
    asers
    -0.58
     enriched
    -0.56
    arers
    -0.55
     kilograms
    -0.55
    POSITIVE LOGITS
    /"
    0.89
     âĢķ
    0.82
    >>\
    0.75
    #$
    0.67
    ?!"
    0.67
    ?"
    0.66
    ""
    0.66
    terday
    0.65
     exclaim
    0.62
    ?'"
    0.61
    Activations Density 0.053%

    No Known Activations