© 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. 18915
    Prev
    Next
    INDEX
    Explanations

    information related to technology and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health care and community services

    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
    ̶
    -0.68
    $.
    -0.65
    ratom
    -0.63
    chwitz
    -0.59
    î
    -0.59
    `.
    -0.59
    ....
    -0.56
    DonaldTrump
    -0.54
    ushima
    -0.54
    olkien
    -0.54
    POSITIVE LOGITS
     consists
    0.91
     consisted
    0.88
     includes
    0.88
     meanwhile
    0.86
     comprises
    0.80
     refers
    0.75
     corresponds
    0.72
     spokesperson
    0.72
     portion
    0.71
     additions
    0.71
    Activations Density 1.013%

    No Known Activations