© 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. 10-RES-JB
    11. 20367
    Prev
    Next
    INDEX
    Explanations

    expressions indicating surprise or unexpected outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the expectation of surprise or the state of being taken aback

    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
    ebted
    -0.71
     Logged
    -0.69
    neys
    -0.61
    oller
    -0.58
    ney
    -0.58
    them
    -0.57
    ter
    -0.56
     Attributes
    -0.55
    tery
    -0.55
     filibuster
    -0.54
    POSITIVE LOGITS
     unsur
    0.81
     no
    0.72
    pires
    0.72
     follows
    0.70
     surprise
    0.68
    pired
    0.68
     shock
    0.68
    ynchron
    0.67
     unwelcome
    0.67
     far
    0.67
    Activations Density 0.039%

    No Known Activations