© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "lol" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter or humor expressions

    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
    rament
    -0.79
     glim
    -0.77
     bounds
    -0.73
    éĹ
    -0.72
    ãĤ©
    -0.72
    ":["
    -0.69
    arnaev
    -0.65
    States
    -0.64
    legates
    -0.64
     contracted
    -0.64
    POSITIVE LOGITS
    ipop
    1.37
    ita
    1.17
    cow
    1.05
    cats
    1.01
    ogie
    0.84
    zers
    0.81
    ibaba
    0.78
    hattan
    0.77
    creen
    0.77
    ogy
    0.73
    Activations Density 0.028%

    No Known Activations