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. 184
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing surprise or shock

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shock or dismay regarding various situations or events

    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
    ãģ®éŃĶ
    -0.84
    igmatic
    -0.73
    ontent
    -0.72
    iac
    -0.72
    MX
    -0.69
    isSpecialOrderable
    -0.69
    soDeliveryDate
    -0.68
    jah
    -0.66
    ectomy
    -0.66
    cano
    -0.64
    POSITIVE LOGITS
     how
    1.14
     seeing
    0.98
     what
    0.95
     lack
    0.91
     witnessing
    0.90
     suggestions
    0.89
     developments
    0.87
     hearing
    0.85
     losing
    0.82
     perceived
    0.81
    Activations Density 0.198%

    No Known Activations