© 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. 3-RES-JB
    11. 9282
    Prev
    Next
    INDEX
    Explanations

    the word "wonder" appearing in sentences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of astonishment or incredulity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.90
    ĪĴ
    -0.83
    etitive
    -0.79
    alach
    -0.75
    ategory
    -0.71
    apsed
    -0.68
    interstitial
    -0.67
    iosis
    -0.67
    ederal
    -0.66
    Ĥ¬
    -0.65
    POSITIVE LOGITS
     aloud
    1.03
     why
    0.81
     wonder
    0.75
    Discuss
    0.74
    iously
    0.72
     WHY
    0.70
     rhet
    0.68
    ously
    0.68
    fully
    0.67
    vale
    0.67
    Activations Density 0.010%

    No Known Activations