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. 3731
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with the word "Then"

    oai_token-act-pair · gpt-3.5-turbo

    sequential phrases or directives in the text

    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
     dating
    -0.67
     interests
    -0.63
     primarily
    -0.59
     sporting
    -0.59
     classified
    -0.58
     engineering
    -0.58
     best
    -0.58
     character
    -0.57
     pun
    -0.57
     existing
    -0.56
    POSITIVE LOGITS
    Then
    3.35
     Then
    2.42
    then
    2.31
     THEN
    2.13
    Eventually
    1.73
    Finally
    1.65
    Later
    1.64
     Afterwards
    1.60
    Secondly
    1.60
     then
    1.60
    Activations Density 0.016%

    No Known Activations