© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    names of artists and related information

    oai_token-act-pair · gpt-3.5-turbo

    references to artists and their works

    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
     ObamaCare
    -0.97
    amacare
    -0.91
     Obamacare
    -0.88
    Senate
    -0.79
     Comcast
    -0.78
     HHS
    -0.78
     timeout
    -0.78
     MMR
    -0.77
     actu
    -0.76
     SEC
    -0.74
    POSITIVE LOGITS
     artwork
    1.43
     painter
    1.41
     paintings
    1.36
     sculpture
    1.35
     artist
    1.34
     sculptures
    1.34
     artistic
    1.31
     artists
    1.28
     art
    1.27
     mural
    1.24
    Activations Density 1.568%

    No Known Activations