© 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. 8-RES-JB
    11. 12919
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of "meta" and related terms in the context of analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ivity
    -0.74
    ibility
    -0.72
    shire
    -0.71
    iens
    -0.69
    ieve
    -0.68
    IBLE
    -0.67
    mable
    -0.65
     Flore
    -0.65
     Franks
    -0.64
     Lauder
    -0.63
    POSITIVE LOGITS
    plot
    1.09
    ethical
    1.00
    verse
    0.99
    alyses
    0.93
    research
    0.81
    enter
    0.79
    allo
    0.78
    hack
    0.73
    uled
    0.72
    uling
    0.71
    Activations Density 0.036%

    No Known Activations