© 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. 8-RES-JB
    11. 14256
    Prev
    Next
    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating deadlines or completion dates

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    SPONSORED
    -0.75
     existed
    -0.62
     "$:/
    -0.62
    Icon
    -0.61
     apart
    -0.60
    butt
    -0.60
     prejudices
    -0.60
    ptions
    -0.59
     pains
    -0.59
    Journal
    -0.58
    POSITIVE LOGITS
     virtue
    1.08
     2030
    1.06
     2020
    1.05
     2025
    1.04
     2050
    1.03
    catch
    1.03
     2021
    1.02
     2022
    0.97
     2024
    0.95
    election
    0.92
    Activations Density 0.105%

    No Known Activations