© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    timestamped political mentions in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to numerical values and their formatting in a political context

    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
     Pros
    -0.73
     Origin
    -0.67
     Brut
    -0.64
     Dud
    -0.60
     Worldwide
    -0.60
     Clim
    -0.59
     Dele
    -0.59
     Converted
    -0.59
     Paradise
    -0.59
     Habit
    -0.59
    POSITIVE LOGITS
    ovember
    0.94
    xff
    0.74
    utterstock
    0.74
    lvl
    0.71
    encing
    0.71
    å¹
    0.69
    ÙIJ
    0.68
    Aug
    0.68
    izations
    0.67
    etsu
    0.67
    Activations Density 0.046%

    No Known Activations