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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 10104
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Courant" or "Cour" which could be related to a newspaper or legal context

    oai_token-act-pair · gpt-3.5-turbo

    Occurrences of the word "Cour" and its variations, suggesting a focus on legal or court-related topics

    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
    WA
    -0.68
     pie
    -0.68
    origin
    -0.67
    iland
    -0.65
     linkage
    -0.65
    weight
    -0.64
    iso
    -0.63
    miah
    -0.62
    plug
    -0.62
    idae
    -0.62
    POSITIVE LOGITS
     Cour
    4.22
    Cour
    2.58
     COUR
    1.98
    cour
    1.80
     cour
    1.65
     Course
    1.41
     courthouse
    1.29
     courses
    1.20
    Course
    1.18
     Jur
    1.07
    Activations Density 0.011%

    No Known Activations