© 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. 9-RES-JB
    11. 10263
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is merely a representation or concept, rather than a concrete reality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is a trivial or minor issue

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    successfully
    -0.77
    lees
    -0.76
    ornia
    -0.74
    2020
    -0.73
    cue
    -0.73
    inguished
    -0.72
    pora
    -0.71
     lest
    -0.70
     Notably
    -0.70
    Only
    -0.69
    POSITIVE LOGITS
     coincidence
    1.08
     placeholder
    1.03
     decoration
    0.91
     curiosity
    0.86
     footnote
    0.86
     fig
    0.85
     plain
    0.85
     nuisance
    0.84
     matter
    0.82
     conduit
    0.82
    Activations Density 0.133%

    No Known Activations