© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20951
    Prev
    Next
    INDEX
    Explanations

    adverbs and phrases related to time, specifically referring to the time "yesterday."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "yesterday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.85
    eers
    -0.85
    ordes
    -0.84
    laus
    -0.76
    anchester
    -0.76
    eer
    -0.75
    onne
    -0.74
    ologne
    -0.73
    onite
    -0.72
    adders
    -0.70
    POSITIVE LOGITS
     afternoon
    1.24
     morning
    1.21
     evening
    1.07
     yesterday
    1.06
     mornings
    1.02
     night
    0.88
    Yesterday
    0.85
     Tuesday
    0.84
     roundup
    0.83
     Thursday
    0.82
    Activations Density 0.012%

    No Known Activations