© 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. 17146
    Prev
    Next
    INDEX
    Explanations

    specific character sequences that seem to have no particular theme or commonality

    oai_token-act-pair · gpt-3.5-turbo

    the special character "ÃĹ" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    aceutical
    -0.79
    rites
    -0.72
    idity
    -0.72
    entious
    -0.71
    mie
    -0.71
    essage
    -0.69
     compr
    -0.69
    ony
    -0.69
    jri
    -0.68
    bably
    -0.67
    POSITIVE LOGITS
     Expand
    0.92
    ÃĹ
    0.86
    LAB
    0.81
    _>
    0.81
    âĶĢâĶĢâĶĢâĶĢ
    0.75
    cus
    0.72
    Python
    0.72
    [[
    0.70
    UX
    0.68
    Pict
    0.68
    Activations Density 0.008%

    No Known Activations