© 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. 8-RES-JB
    11. 7804
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" indicating specific dates or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynt
    -0.72
    arat
    -0.71
    anan
    -0.69
    $$
    -0.68
    oler
    -0.66
    arth
    -0.64
    utter
    -0.62
    aturated
    -0.61
    uum
    -0.61
    aults
    -0.60
    POSITIVE LOGITS
     behalf
    1.45
     Thursday
    1.09
     Wednesday
    1.05
     Monday
    1.03
    shore
    1.02
     Friday
    1.02
     September
    1.01
    etime
    1.01
     Tuesday
    1.00
    erous
    0.99
    Activations Density 0.182%

    No Known Activations