© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3364
    Prev
    Next
    INDEX
    Explanations

    the word "course" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to educational courses or courses of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.81
    nesday
    -0.71
    mented
    -0.71
    gie
    -0.64
    uggets
    -0.62
    ry
    -0.62
    nect
    -0.61
    erd
    -0.60
     spat
    -0.59
    arijuana
    -0.58
    POSITIVE LOGITS
    course
    0.99
    ourses
    0.94
    Course
    0.89
    books
    0.88
     Course
    0.84
    work
    0.81
    washer
    0.81
     instructors
    0.78
     courses
    0.77
    path
    0.76
    Activations Density 0.018%

    No Known Activations