© 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 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. 4-RES-JB
    11. 4903
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an emphasis on certainty or emphasis on a particular point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or limitations

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

    No Comments

    Negative Logits
     tickets
    -0.67
    erva
    -0.61
     Byrd
    -0.61
     UW
    -0.61
     ticket
    -0.59
    EStream
    -0.58
     Cla
    -0.58
     Union
    -0.58
     Bundes
    -0.57
     WM
    -0.57
    POSITIVE LOGITS
     whatsoever
    0.97
    lishes
    0.87
    mite
    0.74
     endorse
    0.73
    isal
    0.71
     resembles
    0.71
    specified
    0.71
    idental
    0.70
     imaginable
    0.69
     resembling
    0.68
    Activations Density 0.056%

    No Known Activations