© 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. 0-RES-JB
    11. 20266
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    allo
    -0.72
    phasis
    -0.70
    etics
    -0.67
    ipes
    -0.63
    hesive
    -0.62
    izo
    -0.60
    bender
    -0.59
    appro
    -0.59
    ennes
    -0.59
    assert
    -0.58
    POSITIVE LOGITS
     day
    3.46
    day
    2.55
     Day
    2.38
    Day
    2.34
     DAY
    2.30
     night
    2.05
     morning
    2.04
     week
    1.89
    DAY
    1.87
     afternoon
    1.83
    Activations Density 0.044%

    No Known Activations