© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 21298
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific character or movie title containing the word "mat"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "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
    IDES
    -0.71
     toast
    -0.64
     Idle
    -0.63
    INTER
    -0.63
    æĸ¹
    -0.62
    CRIP
    -0.62
     stock
    -0.62
    HOME
    -0.61
    éĹĺ
    -0.60
     lightly
    -0.60
    POSITIVE LOGITS
    hemat
    1.41
    mat
    1.28
    hematic
    1.15
    hematically
    1.07
    rix
    1.02
    ches
    0.95
    opol
    0.94
    Mat
    0.94
    umbai
    0.93
    istical
    0.93
    Activations Density 0.007%

    No Known Activations