© 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. 14291
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects of various circumstances or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the effects and impacts of various phenomena

    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
    thia
    -0.86
     largeDownload
    -0.79
    esse
    -0.75
    arta
    -0.74
     istg
    -0.72
    earchers
    -0.69
    swick
    -0.69
    gdala
    -0.68
    lette
    -0.68
    ASE
    -0.67
    POSITIVE LOGITS
     globalization
    0.96
     inaction
    0.89
     repealing
    0.88
     legalizing
    0.88
     changing
    0.86
     electing
    0.86
     these
    0.81
     altering
    0.79
     reducing
    0.79
     removing
    0.78
    Activations Density 0.129%

    No Known Activations