© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 24043
    Prev
    Next
    INDEX
    Explanations

    the name "Mat" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mat" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ITED
    -0.63
     interception
    -0.63
     downhill
    -0.59
     Colossus
    -0.59
     prevailed
    -0.58
     bordering
    -0.58
     Butterfly
    -0.58
     GDDR
    -0.58
     phosphate
    -0.57
     corros
    -0.57
    POSITIVE LOGITS
    hews
    1.43
    hematic
    1.40
    hew
    1.29
    ches
    1.28
    urity
    1.27
    ilda
    1.24
    terson
    1.16
    hemat
    1.08
    chers
    1.08
    ched
    1.07
    Activations Density 0.033%

    No Known Activations