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. 0-RES-JB
    6. 16343
    Prev
    Next
    INDEX
    Explanations

    performing actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "performing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uer
    -0.77
     straw
    -0.71
    ooked
    -0.66
    eur
    -0.66
    utm
    -0.63
    Bul
    -0.62
    pdf
    -0.62
    cern
    -0.61
    onet
    -0.61
    agraph
    -0.60
    POSITIVE LOGITS
     performing
    3.63
     perform
    2.34
    performing
    2.29
     performs
    2.22
     performed
    1.97
     performer
    1.91
     performers
    1.86
     executing
    1.64
     Perform
    1.60
     conducting
    1.59
    Activations Density 0.015%

    No Known Activations