© 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. 10-RES-JB
    11. 18509
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with a tone of surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express surprise or disbelief

    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
     volunte
    -0.84
    hesda
    -0.83
     affili
    -0.81
     prosec
    -0.79
     bonded
    -0.79
     compet
    -0.78
     carbohyd
    -0.77
     strugg
    -0.76
     conduc
    -0.76
     transact
    -0.75
    POSITIVE LOGITS
     Suddenly
    1.59
     Then
    1.45
     Apparently
    1.38
     Eventually
    1.38
     Surely
    1.36
     Turns
    1.34
     Immediately
    1.33
     Within
    1.32
     Was
    1.32
     Somehow
    1.29
    Activations Density 0.381%

    No Known Activations