© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1410
    Prev
    Next
    INDEX
    Explanations

    phrases related to the holiday season, particularly Christmas

    oai_token-act-pair · gpt-3.5-turbo

    references to Christmas

    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
    ocity
    -0.87
     WP
    -0.75
     Radius
    -0.72
    ourses
    -0.71
    INTON
    -0.69
     PW
    -0.68
    />
    -0.68
     UA
    -0.67
    bett
    -0.66
    voc
    -0.65
    POSITIVE LOGITS
     Christmas
    3.78
    Christmas
    3.21
     Thanksgiving
    2.38
     Halloween
    2.18
     Easter
    2.01
     festive
    1.99
     holiday
    1.97
     holidays
    1.84
     Valentine
    1.84
     Holiday
    1.81
    Activations Density 0.009%

    No Known Activations