© 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. 2-RES-JB
    11. 434
    Prev
    Next
    INDEX
    Explanations

    the word "Santa," possibly in the context of a name or title

    oai_token-act-pair · gpt-4-turbo

    proper nouns related to locations, specifically those starting with "Santa"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Santa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edly
    -0.73
    ochond
    -0.69
    ives
    -0.67
    td
    -0.65
    points
    -0.65
    staking
    -0.64
    STD
    -0.64
    hower
    -0.63
    widget
    -0.63
    draw
    -0.62
    POSITIVE LOGITS
     Claus
    1.52
     Clara
    1.07
     Santa
    1.07
     Ana
    0.94
     Monica
    0.93
    Santa
    0.91
     Barbara
    0.87
     Rosa
    0.84
     Cruz
    0.83
     Maria
    0.82
    Activations Density 0.008%

    No Known Activations