© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5120
    Prev
    Next
    INDEX
    Explanations

    years or time-related information, particularly focusing on the past

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of the word "last" indicating time references or durations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    onto
    -0.67
    kefeller
    -0.62
    aband
    -0.61
    OPLE
    -0.61
    obin
    -0.60
     OMG
    -0.58
     Lau
    -0.57
    henko
    -0.57
    cks
    -0.56
     LB
    -0.55
    POSITIVE LOGITS
     Updated
    1.12
     Modified
    1.07
     edited
    1.01
     modified
    1.00
     Edited
    0.99
     bumped
    0.96
     updated
    0.95
     rites
    0.94
     Revised
    0.92
    updated
    0.89
    Activations Density 0.030%

    No Known Activations