© 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. 15618
    Prev
    Next
    INDEX
    Explanations

    keywords related to trend analysis

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to trends and trend analysis

    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
    intent
    -0.72
     Frie
    -0.64
     balloons
    -0.63
     gor
    -0.62
     brewed
    -0.62
    ONES
    -0.62
     Myanmar
    -0.61
     mound
    -0.60
     totem
    -0.60
     Scy
    -0.59
    POSITIVE LOGITS
    Ħ¢
    0.71
    adelphia
    0.71
    Vision
    0.70
    cru
    0.70
     Vision
    0.70
    ution
    0.68
    usk
    0.68
     Sterling
    0.67
     Reduced
    0.67
    alsh
    0.66
    Activations Density 0.000%

    No Known Activations