© 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. 0-RES-JB
    11. 12107
    Prev
    Next
    INDEX
    Explanations

    references to the word "Holiday" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to holidays

    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
     situ
    -0.88
     scrut
    -0.80
     pit
    -0.78
     cy
    -0.78
     comb
    -0.73
     caps
    -0.72
    utan
    -0.71
     brace
    -0.70
     corpor
    -0.69
     minded
    -0.67
    POSITIVE LOGITS
     Holiday
    3.48
     Hilton
    1.43
    iday
    1.29
     Payne
    1.28
     Marriott
    1.20
     McGee
    1.17
    Hol
    0.96
     Harrington
    0.96
     Ingram
    0.95
     Boo
    0.95
    Activations Density 0.044%

    No Known Activations