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. 11-RES-JB
    6. 17903
    Prev
    Next
    INDEX
    Explanations

    future time expressions or events scheduled to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    references to scheduled events and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fail
    -0.70
    inary
    -0.59
     Kills
    -0.59
     Seym
    -0.58
    cial
    -0.57
     Difference
    -0.57
     vomit
    -0.56
    corruption
    -0.55
    iki
    -0.55
     Compared
    -0.54
    POSITIVE LOGITS
     slated
    1.68
     expected
    1.67
     scheduled
    1.65
     planned
    1.38
     anticipated
    1.34
    expected
    1.17
     projected
    1.11
     set
    1.09
     forecast
    1.09
     likely
    1.07
    Activations Density 0.198%

    No Known Activations