© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1794
    Prev
    Next
    INDEX
    Explanations

    exclamations of surprise or realization

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or realization, specifically those framed as "Oh."

    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
     further
    -0.70
     copy
    -0.70
     detailed
    -0.68
     consistent
    -0.67
     results
    -0.66
     timely
    -0.65
     close
    -0.65
     set
    -0.65
     sufficient
    -0.65
     track
    -0.65
    POSITIVE LOGITS
    Oh
    3.27
     Oh
    2.23
    Ah
    1.92
     oh
    1.89
    Uh
    1.81
    oh
    1.74
    Wow
    1.71
    Yeah
    1.69
    Huh
    1.67
    Hmm
    1.66
    Activations Density 0.016%

    No Known Activations