© 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. 2-RES-JB
    11. 8926
    Prev
    Next
    INDEX
    Explanations

    titles or references to winning or competing for titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "title" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gm
    -0.78
    hari
    -0.64
    obb
    -0.63
    olson
    -0.63
    ierrez
    -0.63
     Leone
    -0.63
     isot
    -0.62
     ears
    -0.62
     Alto
    -0.62
    ombo
    -0.62
    POSITIVE LOGITS
    title
    1.11
     title
    0.97
     titles
    0.96
    manship
    0.91
    ¥µ
    0.89
    marks
    0.86
    sworth
    0.81
    lord
    0.79
    ãĥĩ
    0.73
    holder
    0.71
    Activations Density 0.011%

    No Known Activations