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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13971
    Prev
    Next
    INDEX
    Explanations

    dates and times in the format of "m. ET"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "ET" and its context in reporting time

    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
    Ry
    -0.71
    Rated
    -0.66
     Ry
    -0.64
    anus
    -0.63
     shr
    -0.63
     Prosecut
    -0.62
     bay
    -0.61
     Rh
    -0.61
    ophon
    -0.61
    iny
    -0.60
    POSITIVE LOGITS
     ET
    4.09
     PT
    1.64
     EST
    1.62
    ET
    1.50
     EDT
    1.45
     CET
    1.34
     CST
    1.32
     EW
    1.29
     IST
    1.29
     CT
    1.25
    Activations Density 0.020%

    No Known Activations