© 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. 1-RES-JB
    11. 20438
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, particularly one side of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "side."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ancies
    -0.71
     "$:/
    -0.67
    iott
    -0.67
    ãģ®éŃĶ
    -0.65
    cci
    -0.63
     Gutenberg
    -0.63
    amiliar
    -0.62
     contagious
    -0.62
    iona
    -0.61
    URES
    -0.61
    POSITIVE LOGITS
    side
    1.28
    ward
    0.81
    wards
    0.81
    TextColor
    0.81
    Edge
    0.78
    mast
    0.78
    Side
    0.77
    kick
    0.74
    medi
    0.74
    boarding
    0.73
    Activations Density 0.006%

    No Known Activations