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. 1-RES-JB
    6. 13704
    Prev
    Next
    INDEX
    Explanations

    instances where the term "eventually" is used in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Eventually" and "Ultimately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uns
    -0.74
    prim
    -0.72
    coord
    -0.72
    ucc
    -0.68
    marked
    -0.68
    que
    -0.67
    urg
    -0.65
     guaranteed
    -0.63
    ighty
    -0.62
    powder
    -0.61
    POSITIVE LOGITS
    SourceFile
    1.05
    Eventually
    0.81
    theless
    0.77
     Canaver
    0.76
    etheless
    0.76
    imaru
    0.73
     Events
    0.70
    wcs
    0.69
    Iterator
    0.69
    terness
    0.69
    Activations Density 0.006%

    No Known Activations