© 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. 18286
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing a point

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include "of course."

    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
    Sold
    -0.74
    ulously
    -0.71
    aband
    -0.69
    chel
    -0.69
    lean
    -0.65
    creen
    -0.64
    ayn
    -0.64
    ļéĨĴ
    -0.64
    bands
    -0.64
    ¥µ
    -0.63
    POSITIVE LOGITS
    ierre
    0.68
    icio
    0.64
     causation
    0.63
     ACTIONS
    0.62
     Kinnikuman
    0.60
     convergence
    0.59
     depending
    0.58
    xual
    0.57
     excluding
    0.57
    orney
    0.57
    Activations Density 0.159%

    No Known Activations