© 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. 20452
    Prev
    Next
    INDEX
    Explanations

    names of people in news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with individuals or entities

    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
    aged
    -0.84
    tons
    -0.81
    dit
    -0.79
    noon
    -0.76
    ahime
    -0.76
    ragon
    -0.75
    many
    -0.73
     Totem
    -0.73
    berry
    -0.70
    age
    -0.69
    POSITIVE LOGITS
     fn
    1.08
    fn
    0.81
    FN
    0.77
    pload
    0.75
     tremend
    0.73
    umpy
    0.73
    umbnails
    0.72
    ilee
    0.70
    ļéĨĴ
    0.69
     guiActiveUn
    0.68
    Activations Density 0.024%

    No Known Activations