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. 14193
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that an event or process is in progress

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "underway" in various contexts, indicating ongoing actions or processes

    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
    attribute
    -0.62
     Blaze
    -0.58
    rose
    -0.55
    api
    -0.55
    fuck
    -0.55
    ey
    -0.54
    android
    -0.54
     Element
    -0.54
    e
    -0.54
    angs
    -0.54
    POSITIVE LOGITS
     underway
    3.47
     undertaken
    1.25
     commenced
    1.18
     ongoing
    1.17
     unfolding
    1.12
     overdue
    1.07
     begun
    1.03
     occurring
    1.01
     happening
    1.01
     commence
    1.01
    Activations Density 0.015%

    No Known Activations