Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7665
    Prev
    Next
    INDEX
    Explanations

    references to gift-giving and the concept of Santa Claus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to the activity of giving or receiving gifts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournals
    -0.77
    inki
    -0.72
     Democr
    -0.65
     campuses
    -0.64
     zones
    -0.63
    othal
    -0.61
    aints
    -0.61
    und
    -0.61
     reservoirs
    -0.60
    unda
    -0.60
    POSITIVE LOGITS
     Claus
    1.21
     gift
    0.86
    Santa
    0.82
     Gifts
    0.80
     gifts
    0.79
     Geek
    0.77
     Gift
    0.76
    mas
    0.76
    !!!!!
    0.76
    !!!!
    0.75
    Activations Density 0.071%

    No Known Activations