© 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. 6-RES-JB
    11. 5127
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prices and numerical quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLS
    -0.56
    Profile
    -0.55
    Scene
    -0.54
    ESE
    -0.54
     AND
    -0.54
    benefit
    -0.54
    quote
    -0.50
    stuff
    -0.50
     and
    -0.50
    payers
    -0.49
    POSITIVE LOGITS
     thereafter
    0.89
     respectively
    0.86
     alike
    0.78
     versa
    0.75
     Cind
    0.67
     afterward
    0.66
    lishes
    0.65
    bernatorial
    0.62
    è£ħ
    0.62
    ilus
    0.61
    Activations Density 0.602%

    No Known Activations