© 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. 0-RES-JB
    11. 22332
    Prev
    Next
    INDEX
    Explanations

    buzzwords or trendy terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to popularity or excitement, particularly the term "buzz"

    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
    arent
    -0.70
    VS
    -0.69
    atern
    -0.68
     Settlement
    -0.68
     Reconstruction
    -0.67
    write
    -0.67
    render
    -0.65
    tein
    -0.65
    instance
    -0.64
    stein
    -0.64
    POSITIVE LOGITS
     buzz
    4.01
     buzzing
    2.00
     Buzz
    1.73
    Buzz
    1.64
     hype
    1.54
     chatter
    1.53
     excitement
    1.11
     euph
    1.05
     hust
    1.04
     vibe
    1.04
    Activations Density 0.018%

    No Known Activations