© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    references to actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to community support and activism

    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
    âĢIJ
    -0.74
    [/
    -0.72
     Writ
    -0.72
     thee
    -0.72
    '>
    -0.70
     Supplementary
    -0.69
     ['
    -0.69
     Assass
    -0.67
     Sect
    -0.67
     ('
    -0.67
    POSITIVE LOGITS
     tourists
    0.80
    ¬¼
    0.80
    Redd
    0.79
     regulars
    0.74
     teenagers
    0.73
     prank
    0.72
    Kids
    0.71
     locals
    0.70
    tnc
    0.69
     teens
    0.68
    Activations Density 1.532%

    No Known Activations