© 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. 10-RES-JB
    11. 18865
    Prev
    Next
    INDEX
    Explanations

    periods

    oai_token-act-pair · gpt-3.5-turbo

    punctuation at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogene
    -0.63
    vine
    -0.62
    pires
    -0.61
    icent
    -0.60
    inous
    -0.60
     sergeant
    -0.59
    uner
    -0.59
    itely
    -0.59
    idious
    -0.58
     genus
    -0.58
    POSITIVE LOGITS
     Additionally
    1.51
     However
    1.50
     Those
    1.48
     Their
    1.44
     They
    1.44
     Though
    1.41
     Although
    1.41
     According
    1.41
     Unfortunately
    1.41
     These
    1.41
    Activations Density 0.126%

    No Known Activations