© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15046
    Prev
    Next
    INDEX
    Explanations

    instances of applause or cheering

    oai_token-act-pair · gpt-3.5-turbo

    instances of applause or expressions of approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    voy
    -0.72
     researched
    -0.72
    vati
    -0.69
    quel
    -0.68
     metic
    -0.66
    ahime
    -0.66
     Anthrop
    -0.66
    nia
    -0.65
     wounds
    -0.64
    earcher
    -0.63
    POSITIVE LOGITS
     cheers
    1.16
     applause
    1.03
     cheering
    1.02
    hovah
    0.93
     cheered
    0.92
     applaud
    0.85
     laughter
    0.83
     voic
    0.79
     applauded
    0.77
     louder
    0.72
    Activations Density 0.015%

    No Known Activations