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. 21558
    Prev
    Next
    INDEX
    Explanations

    instances related to improvement or betterment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "improve."

    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
     Pri
    -0.73
     Bild
    -0.69
     Chains
    -0.62
     subpoen
    -0.61
     Zeit
    -0.61
    wic
    -0.61
     Held
    -0.61
     Orders
    -0.60
    ls
    -0.60
     Television
    -0.59
    POSITIVE LOGITS
     improve
    3.20
    improve
    2.32
     Improve
    2.32
     improves
    2.27
     improving
    2.23
    Improve
    2.15
     improvement
    1.99
     improved
    1.96
     enhance
    1.93
     optimize
    1.86
    Activations Density 0.025%

    No Known Activations