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. 1-RES-JB
    6. 1558
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "exclamation"

    oai_token-act-pair · gpt-3.5-turbo

    exclamations and quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NEC
    -0.68
    abol
    -0.68
     steep
    -0.64
     Hodg
    -0.62
    GO
    -0.59
    Bra
    -0.58
     constitu
    -0.58
     SEN
    -0.57
     neuroscience
    -0.56
    Downloadha
    -0.56
    POSITIVE LOGITS
    clamation
    1.25
    naire
    1.07
    oons
    0.78
    prises
    0.75
    prise
    0.75
    ures
    0.75
    issance
    0.74
    ptives
    0.74
    pell
    0.73
    ptions
    0.71
    Activations Density 0.005%

    No Known Activations