© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21146
    Prev
    Next
    INDEX
    Explanations

    adverbs that end in 'ly'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate self-identification or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.63
    crop
    -0.62
     Shows
    -0.61
     Frie
    -0.58
    enting
    -0.58
    onto
    -0.57
     Lighting
    -0.57
    ventures
    -0.56
     Story
    -0.56
    udeau
    -0.56
    POSITIVE LOGITS
     term
    1.69
     termed
    1.68
     euphem
    1.65
     refer
    1.48
     referred
    1.44
     terminology
    1.44
     called
    1.37
     dubbed
    1.32
     nicknamed
    1.32
     moniker
    1.29
    Activations Density 0.602%

    No Known Activations