© 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. 0-RES-JB
    11. 5139
    Prev
    Next
    INDEX
    Explanations

    mentions of words related to sprinkling or spreading

    oai_token-act-pair · gpt-3.5-turbo

    words related to sparkle or shine and the concept of twinkling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hol
    -0.69
     Theresa
    -0.66
    gat
    -0.64
    journal
    -0.63
     conversion
    -0.63
    ering
    -0.62
     writ
    -0.62
    Brexit
    -0.62
     Evans
    -0.62
     nom
    -0.61
    POSITIVE LOGITS
    inkle
    2.95
     Razor
    2.28
     Tide
    1.26
     Ricardo
    1.14
    azor
    1.07
     Lar
    1.05
     Longh
    1.04
     Avalanche
    1.03
     Sands
    1.02
    ":["
    0.99
    Activations Density 0.044%

    No Known Activations