© 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. 8-RES-JB
    11. 4939
    Prev
    Next
    INDEX
    Explanations

    expressions conveying astonishment or surprise

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating feelings of astonishment or discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - surprise

    No Comments

    Negative Logits
    jong
    -0.76
    chlor
    -0.66
    oby
    -0.66
    urred
    -0.65
    æĿ
    -0.65
    iverpool
    -0.65
    iliated
    -0.64
     streng
    -0.64
    escription
    -0.64
    aith
    -0.63
    POSITIVE LOGITS
    ioned
    0.75
     why
    0.70
    lessness
    0.68
     nobody
    0.67
     fools
    0.64
     Dems
    0.63
     they
    0.63
     THEY
    0.63
     Giuliani
    0.62
     Governments
    0.62
    Activations Density 0.105%

    No Known Activations