Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 2150
    Prev
    Next
    INDEX
    Explanations

    emotions and reactions related to surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    moments of surprise or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 10 - surprise

    No Comments

    Negative Logits
    camp
    -0.79
    İĭ
    -0.76
    ngth
    -0.75
    conservancy
    -0.74
    hang
    -0.70
     vend
    -0.69
    oku
    -0.68
    ongo
    -0.67
    hunt
    -0.65
    hod
    -0.62
    POSITIVE LOGITS
     seeing
    1.09
     hearing
    1.09
     witnessing
    1.02
     discovering
    0.98
     realizing
    0.95
     reading
    0.93
     heard
    0.91
     realised
    0.90
     Seeing
    0.89
     realization
    0.89
    Activations Density 0.211%

    No Known Activations