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. 22830
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific regions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the word "Greater" in various contexts

    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
    locks
    -0.75
    jac
    -0.64
    lock
    -0.64
    æ
    -0.62
     repro
    -0.61
    Äį
    -0.61
     intrig
    -0.61
    ´
    -0.61
     acne
    -0.60
    akov
    -0.60
    POSITIVE LOGITS
     Greater
    3.91
    Great
    1.59
     greater
    1.41
     Lower
    1.28
     Great
    1.26
     Less
    1.17
     Higher
    1.17
     Metropolitan
    1.11
     Inner
    1.10
     Faster
    1.07
    Activations Density 0.019%

    No Known Activations