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. 10-RES-JB
    6. 22561
    Prev
    Next
    INDEX
    Explanations

    any instance of the word "else"

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning alternatives or additional possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mehran
    -0.68
     Abstract
    -0.62
    gers
    -0.61
    forestation
    -0.61
    tein
    -0.61
    acity
    -0.60
     Encyclopedia
    -0.60
    Upload
    -0.59
    ge
    -0.59
    ousands
    -0.58
    POSITIVE LOGITS
    worldly
    1.31
     besides
    1.00
     entirely
    0.81
    where
    0.75
    mia
    0.71
    cooked
    0.67
    ptive
    0.66
     nearby
    0.66
    .}
    0.65
     includ
    0.65
    Activations Density 0.037%

    No Known Activations