© 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 EvalsExportsinterp-engineNEWAPI 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. 17558
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Express."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Express" in various contexts

    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
    ellen
    -0.80
    aeper
    -0.78
     Ambro
    -0.71
    abama
    -0.69
    ategory
    -0.67
     Icar
    -0.66
    assic
    -0.66
     Griffith
    -0.64
    antically
    -0.63
     Faul
    -0.63
    POSITIVE LOGITS
    Route
    1.06
    Express
    1.00
    ions
    0.89
    ãĥ¼ãĥĨãĤ£
    0.85
    ivity
    0.84
     Express
    0.84
    express
    0.79
    ibe
    0.77
    Act
    0.76
    prise
    0.75
    Activations Density 0.007%

    No Known Activations