© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 9667
    Prev
    Next
    INDEX
    Explanations

    the name "Matthew" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Matthew."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phy
    -0.81
    PLA
    -0.80
    ntil
    -0.79
    ãĥ©ãĥ³
    -0.79
    cknow
    -0.79
    dylib
    -0.78
    ãĤ´ãĥ³
    -0.77
    ãĥīãĥ©ãĤ´ãĥ³
    -0.77
    GROUND
    -0.74
    body
    -0.74
    POSITIVE LOGITS
     Stafford
    0.94
     Matthew
    0.93
     Vaughn
    0.81
     Peters
    0.78
     Shepard
    0.77
     Abraham
    0.77
     Isa
    0.76
     Matthews
    0.76
     Smith
    0.76
    hew
    0.75
    Activations Density 0.004%

    No Known Activations