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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10-RES-JB
    6. 22106
    Prev
    Next
    INDEX
    Explanations

    dates and events related to American holidays, particularly the Fourth of July

    oai_token-act-pair · gpt-3.5-turbo

    references to national holidays, specifically Independence Day and its celebrations

    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
    •shakespeare
    realizes that the "event" is significant

    No Comments

    Negative Logits
    artments
    -0.75
     wiring
    -0.72
     VIDE
    -0.69
    qus
    -0.66
     transcript
    -0.66
    lycer
    -0.65
     conn
    -0.65
    hesive
    -0.65
    jected
    -0.64
    ierrez
    -0.64
    POSITIVE LOGITS
     commemor
    1.27
     commem
    1.20
     celebrations
    1.20
     holiday
    1.18
     celebration
    1.14
     holidays
    1.12
     anniversary
    1.12
     festivities
    1.11
     Feast
    1.09
     Celebr
    1.08
    Activations Density 0.310%

    No Known Activations