© 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. 6-RES-JB
    11. 17671
    Prev
    Next
    INDEX
    Explanations

    the word "big" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or large entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    DragonMagazine
    -0.77
    veyard
    -0.74
    yrinth
    -0.74
     confir
    -0.70
    Dialogue
    -0.70
    cia
    -0.69
     Reincarnated
    -0.68
     Cheong
    -0.68
    chron
    -0.66
    manship
    -0.66
    POSITIVE LOGITS
    oted
    1.21
    gest
    1.03
     ol
    0.98
    wig
    0.97
     chunk
    0.94
    GER
    0.89
    ger
    0.88
     chunks
    0.86
     bang
    0.86
    mouth
    0.83
    Activations Density 0.056%

    No Known Activations