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. 11079
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Mat" preceded by another word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mat"

    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
    ngth
    -0.78
    æĸ¹
    -0.77
    éĹĺ
    -0.67
    é»Ĵ
    -0.67
     nomine
    -0.66
    anwhile
    -0.66
    hower
    -0.63
    ¥ŀ
    -0.62
    ãĤĭ
    -0.62
     confir
    -0.61
    POSITIVE LOGITS
    hematic
    1.32
    hematically
    1.19
    ilda
    1.15
    hews
    1.08
    hemat
    1.07
    rices
    1.03
     Mat
    1.02
    urity
    0.96
    ador
    0.94
    Mat
    0.93
    Activations Density 0.008%

    No Known Activations