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. 8645
    Prev
    Next
    INDEX
    Explanations

    words related to the term "latte"

    oai_token-act-pair · gpt-3.5-turbo

    references to latency and related terms

    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
    ogue
    -0.71
    reau
    -0.71
     Sell
    -0.68
    odge
    -0.68
     Moss
    -0.66
    essential
    -0.66
     Garn
    -0.66
    strate
    -0.66
    ossibility
    -0.65
     Insurance
    -0.65
    POSITIVE LOGITS
     lat
    3.93
     latch
    1.54
    lat
    1.39
     latt
    1.33
     LAT
    1.16
     latitude
    0.96
     bur
    0.95
     americ
    0.95
     laz
    0.94
     tim
    0.94
    Activations Density 0.016%

    No Known Activations