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. 19452
    Prev
    Next
    INDEX
    Explanations

    the word "Then" as a signal or transition point in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "then"

    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
    tein
    -0.78
    undo
    -0.66
    toe
    -0.66
    ties
    -0.64
    chest
    -0.64
    ding
    -0.64
    ching
    -0.63
    ufact
    -0.62
    ulner
    -0.62
    ãĥ³ãĤ¸
    -0.61
    POSITIVE LOGITS
     came
    1.17
     again
    1.09
     comes
    1.06
     there
    0.92
     Comes
    0.89
     arose
    0.86
     suddenly
    0.85
     secondly
    0.84
     proceeded
    0.83
     sprang
    0.79
    Activations Density 0.065%

    No Known Activations