© 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
    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. 12068
    Prev
    Next
    INDEX
    Explanations

    dates in the format month day

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the number 21, particularly in the contexts of dates and timelines

    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
    Interstitial
    -0.71
    channelAvailability
    -0.63
    sei
    -0.62
    milo
    -0.61
    iliate
    -0.61
    èª
    -0.61
    Split
    -0.58
    gow
    -0.58
    uca
    -0.58
    spread
    -0.58
    POSITIVE LOGITS
     21
    3.06
     22
    2.18
     19
    2.07
     23
    1.99
     31
    1.91
     20
    1.86
     26
    1.84
     27
    1.84
     28
    1.79
     17
    1.78
    Activations Density 0.021%

    No Known Activations