Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1474
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the word "Then"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Then" as a narrative transition or connector in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idad
    -0.63
    leading
    -0.59
    making
    -0.57
    borgh
    -0.57
    toe
    -0.57
    single
    -0.56
    ction
    -0.56
    makers
    -0.56
    against
    -0.55
    associated
    -0.55
    POSITIVE LOGITS
     secondly
    0.84
    igslist
    0.75
    Ͻ
    0.75
    adays
    0.75
     proceeded
    0.73
    veland
    0.71
    thodox
    0.71
     conclud
    0.70
    anski
    0.68
     srf
    0.68
    Activations Density 0.038%

    No Known Activations