© 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. 4997
    Prev
    Next
    INDEX
    Explanations

    references to "Moksha," a term related to liberation or freedom in Hinduism and Buddhism

    oai_token-act-pair · gpt-3.5-turbo

    the word "ok" and its variations

    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
     Legions
    -0.69
    oire
    -0.68
     lav
    -0.67
    bugs
    -0.64
    è¦ļéĨĴ
    -0.63
    ORGE
    -0.62
    ordinary
    -0.61
     cort
    -0.60
    Wr
    -0.60
     cows
    -0.59
    POSITIVE LOGITS
    lahoma
    1.10
    unin
    1.04
    nown
    1.00
    awaru
    0.95
    wana
    0.95
    arak
    0.93
    owski
    0.91
    ileaks
    0.90
    ettle
    0.88
    aido
    0.88
    Activations Density 0.020%

    No Known Activations