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. 11-RES-JB
    6. 22406
    Prev
    Next
    INDEX
    Explanations

    sentences starting with the word "According"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "According to" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.69
    DOWN
    -0.65
    krit
    -0.61
     notor
    -0.61
     mathemat
    -0.60
     gobl
    -0.59
     godd
    -0.59
     eleph
    -0.58
     submar
    -0.58
    aden
    -0.56
    POSITIVE LOGITS
    ly
    1.31
     to
    1.03
    edly
    0.95
    lly
    0.90
    LY
    0.83
    itionally
    0.76
    ificantly
    0.73
    views
    0.69
    itely
    0.68
    To
    0.68
    Activations Density 0.038%

    No Known Activations