© 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. 18334
    Prev
    Next
    INDEX
    Explanations

    words related to writing, drawing, or sketching

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "sink" and related forms

    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
     contend
    -0.77
    ãĥ¤
    -0.65
     Sharif
    -0.62
    ãĥ¼ãĥ³
    -0.61
     foundation
    -0.59
    iles
    -0.59
    inance
    -0.59
    pees
    -0.58
    ت
    -0.58
    PF
    -0.58
    POSITIVE LOGITS
    omething
    0.86
     wink
    0.85
    manship
    0.84
    edin
    0.82
    glers
    0.79
    redients
    0.79
    inks
    0.78
    ividual
    0.77
    ertodd
    0.75
    orno
    0.74
    Activations Density 0.010%

    No Known Activations