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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 17296
    Prev
    Next
    INDEX
    Explanations

    the word "Matt" with varying spellings and contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITED
    -0.66
     stock
    -0.61
    RAFT
    -0.60
    âĢİ
    -0.59
     prevailing
    -0.57
     turb
    -0.56
     normalized
    -0.55
     prevail
    -0.55
     outgoing
    -0.55
     Passenger
    -0.53
    POSITIVE LOGITS
    hematically
    1.65
    urity
    1.51
    hews
    1.51
    hematic
    1.50
    hemat
    1.36
    ilda
    1.36
    rices
    1.34
    hew
    1.33
    ches
    1.31
    hes
    1.14
    Activations Density 0.031%

    No Known Activations