Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16790
    Prev
    Next
    INDEX
    Explanations

    text enclosed in square brackets, denoting laughter

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey humor or laughter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purportedly
    -0.70
    ãĥ©ãĥ³
    -0.70
    arak
    -0.69
    onde
    -0.69
    aii
    -0.69
    cgi
    -0.68
    ãĤ·
    -0.67
    mere
    -0.66
    urst
    -0.65
    moil
    -0.62
    POSITIVE LOGITS
    laughs
    0.91
     misunder
    0.85
     reperc
    0.79
     friendships
    0.77
     Defin
    0.77
     reluct
    0.74
     comr
    0.74
     gonna
    0.73
     gotta
    0.71
    Laughs
    0.71
    Activations Density 2.592%

    No Known Activations