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. 335
    Prev
    Next
    INDEX
    Explanations

    adjectives that express surprise or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of interest or remarkable qualities in various subjects

    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
    liv
    -0.75
    onet
    -0.69
    jam
    -0.66
    alone
    -0.61
    chairs
    -0.57
    uffs
    -0.57
    ordon
    -0.57
     Init
    -0.56
    ogens
    -0.56
    inances
    -0.55
    POSITIVE LOGITS
     about
    1.29
     ABOUT
    1.07
     About
    0.97
    about
    0.93
    About
    0.74
     here
    0.68
     regarding
    0.68
    piring
    0.68
    andowski
    0.67
    rous
    0.62
    Activations Density 0.095%

    No Known Activations