© 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. 3-RES-JB
    11. 7066
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities or measures

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving comparisons of quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eye
    -0.76
    ALE
    -0.70
    imity
    -0.69
    pillar
    -0.68
    hran
    -0.68
    ilic
    -0.66
    igl
    -0.66
     Juda
    -0.66
     largeDownload
    -0.65
    aly
    -0.64
    POSITIVE LOGITS
     usual
    0.79
    average
    0.78
    whelming
    0.78
     expected
    0.77
     anticipated
    0.77
     average
    0.74
     satisfactory
    0.69
     compensated
    0.68
     contiguous
    0.67
    whel
    0.67
    Activations Density 0.083%

    No Known Activations