© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4313
    Prev
    Next
    INDEX
    Explanations

    positive adjectives preceded by the phrase "What a"

    oai_token-act-pair · gpt-3.5-turbo

    expressions that highlight strong opinions or emotional responses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.78
    wikipedia
    -0.74
    isSpecialOrderable
    -0.71
    \<
    -0.71
    Accessory
    -0.71
    Recommended
    -0.71
    idas
    -0.68
    istar
    -0.68
    arent
    -0.68
    SI
    -0.68
    POSITIVE LOGITS
     coincidence
    1.28
     difference
    1.16
     wonderful
    1.15
     marvelous
    1.07
     lovely
    1.07
     shame
    1.04
     delightful
    1.02
     hypocr
    1.01
     fantastic
    0.99
     fascinating
    0.98
    Activations Density 0.052%

    No Known Activations