© 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. 0-RES-JB
    6. 4867
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Date" with various numerical identifiers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     stewards
    -0.76
     armour
    -0.65
     popul
    -0.63
     apprentices
    -0.62
     sparing
    -0.62
     flourishing
    -0.62
    astics
    -0.61
     conscious
    -0.61
     sacks
    -0.61
     skilled
    -0.60
    POSITIVE LOGITS
     Date
    3.97
    Date
    2.81
     Dates
    2.45
     date
    2.35
    date
    2.21
     dates
    1.88
     Dating
    1.38
    dates
    1.28
     dated
    1.25
     Birthday
    1.17
    Activations Density 0.019%

    No Known Activations