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. 0-RES-JB
    6. 5824
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "whenever" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whenever."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erville
    -0.61
    olk
    -0.54
     mistaken
    -0.54
     final
    -0.53
     expected
    -0.52
    yet
    -0.52
     Americas
    -0.52
     prelim
    -0.51
    ered
    -0.51
    standing
    -0.50
    POSITIVE LOGITS
     whenever
    3.16
     wherever
    2.15
     Whenever
    2.01
    Whenever
    1.79
     anytime
    1.71
     whichever
    1.50
     periodically
    1.34
     every
    1.32
     whoever
    1.31
    every
    1.30
    Activations Density 0.009%

    No Known Activations