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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12249
    Prev
    Next
    INDEX
    Explanations

    instances of applause and cheers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to applause and public approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     researched
    -0.67
    toe
    -0.67
    cephal
    -0.66
    Travel
    -0.65
    change
    -0.65
     Hayward
    -0.63
     explorer
    -0.62
     resear
    -0.61
    opic
    -0.61
     Wonderland
    -0.60
    POSITIVE LOGITS
     cheers
    1.14
     applause
    1.09
    hovah
    0.98
     cheering
    0.92
     louder
    0.91
     loudly
    0.85
     laughter
    0.84
     voic
    0.83
     cheered
    0.83
     chants
    0.83
    Activations Density 0.022%

    No Known Activations