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. 0-RES-JB
    6. 10662
    Prev
    Next
    INDEX
    Explanations

    instances of the word "course" in varied contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of course."

    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
    isma
    -0.70
    hene
    -0.65
    eland
    -0.65
    anes
    -0.64
    obyl
    -0.59
    keys
    -0.59
    key
    -0.59
    amba
    -0.57
    ank
    -0.56
    uned
    -0.56
    POSITIVE LOGITS
     course
    4.12
    course
    3.21
     Course
    2.92
     COUR
    2.47
    Course
    2.45
     courses
    2.43
    ourses
    1.13
     lesson
    1.09
     trajectory
    1.07
     curriculum
    1.02
    Activations Density 0.036%

    No Known Activations