© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 11060
    Prev
    Next
    INDEX
    Explanations

    references to gifts being sent or received, especially related to a figure like Santa Claus

    oai_token-act-pair · gpt-3.5-turbo

    references to Santa and gift-giving during the holiday season

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lag
    -0.89
    ournals
    -0.72
    inki
    -0.69
    undo
    -0.66
    english
    -0.65
     Democr
    -0.65
    paren
    -0.64
    )].
    -0.63
    runners
    -0.63
    osition
    -0.62
    POSITIVE LOGITS
     Claus
    1.43
     gift
    0.85
     gifts
    0.82
     Gifts
    0.81
    Santa
    0.81
     Crate
    0.77
     Santa
    0.75
     Clause
    0.74
    mas
    0.73
     Gift
    0.72
    Activations Density 0.034%

    No Known Activations