© 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. 13130
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing high intensity or extremeness

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that amplify the qualities of nouns or descriptions

    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
    ULTS
    -0.82
     organs
    -0.77
    lees
    -0.77
     entrants
    -0.75
     lobb
    -0.73
     Challenges
    -0.73
    rients
    -0.72
     Releases
    -0.72
     Eggs
    -0.72
    ults
    -0.71
    POSITIVE LOGITS
     sizable
    0.94
     sizeable
    0.91
     elaborate
    0.89
     diverse
    0.89
     narrow
    0.89
     respectable
    0.88
     complicated
    0.87
     interesting
    0.86
     disproportionate
    0.86
     primitive
    0.86
    Activations Density 0.133%

    No Known Activations