© 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. 4-RES-JB
    11. 22182
    Prev
    Next
    INDEX
    Explanations

    phrases related to New Year's resolutions or celebrations

    oai_token-act-pair · gpt-3.5-turbo

    references to New Year's celebrations and resolutions

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

    No Comments

    Negative Logits
     Cosponsors
    -0.89
    ateral
    -0.88
    PLA
    -0.86
    EStreamFrame
    -0.78
    cro
    -0.75
    »Ĵ
    -0.73
    anooga
    -0.71
    IRC
    -0.68
    developed
    -0.67
    atin
    -0.67
    POSITIVE LOGITS
     Celebration
    0.89
     Eve
    0.89
     anniversary
    0.75
    idia
    0.75
    nings
    0.74
     Ago
    0.72
     festivities
    0.70
     holidays
    0.70
     Anniversary
    0.69
     Edition
    0.68
    Activations Density 0.023%

    No Known Activations