© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19960
    Prev
    Next
    INDEX
    Explanations

    text indicating laughter or amusement, specifically the abbreviation "lol" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of laughter or amusement

    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
    éĹ
    -0.78
    States
    -0.77
    icipated
    -0.75
    ENTS
    -0.73
    ":["
    -0.71
     glim
    -0.70
    Topics
    -0.69
    arnaev
    -0.67
     Phant
    -0.66
    Catal
    -0.65
    POSITIVE LOGITS
    ipop
    1.28
    ita
    1.05
    cow
    1.00
    creen
    0.87
    cats
    0.85
    ipedia
    0.84
    ogie
    0.84
    ibrary
    0.81
     lol
    0.78
    oco
    0.78
    Activations Density 0.013%

    No Known Activations