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. 4532
    Prev
    Next
    INDEX
    Explanations

    comparisons or instances where one item is presented as superior to another

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that involve the word "than."

    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
     MLB
    -0.72
    Chicago
    -0.69
    Jew
    -0.68
    utils
    -0.67
    cre
    -0.67
     exempt
    -0.65
     Cubs
    -0.63
     repro
    -0.63
    import
    -0.63
     pitchers
    -0.62
    POSITIVE LOGITS
     Than
    3.58
     premature
    1.19
     Nguyen
    1.11
    Ton
    0.98
     Chau
    0.96
    ulhu
    0.95
     Ong
    0.94
     Xin
    0.91
     Ultron
    0.89
     Loki
    0.86
    Activations Density 0.031%

    No Known Activations