© 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. 11-RES-JB
    11. 22608
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and elements associated with Christmas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Christmas and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    voc
    -0.76
    SPONSORED
    -0.74
    rahim
    -0.74
    aird
    -0.73
    ioch
    -0.72
    izabeth
    -0.72
    uto
    -0.72
    ocate
    -0.70
    auga
    -0.70
    vae
    -0.69
    POSITIVE LOGITS
     Eve
    1.29
     decorations
    1.02
     Tree
    1.01
     Gifts
    1.00
     eve
    1.00
     Gift
    0.98
     holidays
    0.98
     Carol
    0.96
     Celebration
    0.93
     gift
    0.92
    Activations Density 0.041%

    No Known Activations