© 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. 6-RES-JB
    11. 9574
    Prev
    Next
    INDEX
    Explanations

    direct references to the reader

    oai_token-act-pair · gpt-3.5-turbo

    references to the audience or readers directly

    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
     Heist
    -0.67
     Paddock
    -0.66
     Faul
    -0.63
     Saul
    -0.63
     Monstrous
    -0.62
     Farn
    -0.61
     Charlottesville
    -0.61
     Hick
    -0.61
    assemb
    -0.61
     Mehran
    -0.60
    POSITIVE LOGITS
     guys
    1.04
    tub
    1.04
     yourselves
    0.89
    RS
    0.85
    azeera
    0.81
     know
    0.76
    ters
    0.75
    TER
    0.74
    endi
    0.73
     gentlemen
    0.72
    Activations Density 0.031%

    No Known Activations