© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparative adjectives related to size, power, or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote comparisons of size, magnitude, or quality

    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
    ttes
    -0.79
    iage
    -0.73
    isance
    -0.72
    ODUCT
    -0.68
    iki
    -0.65
     partName
    -0.65
    ISON
    -0.65
    aea
    -0.64
    ESE
    -0.64
    ython
    -0.63
    POSITIVE LOGITS
    liest
    1.29
     fastest
    1.24
    hest
    1.19
     smartest
    1.19
     heaviest
    1.19
     richest
    1.17
     longest
    1.15
     cheapest
    1.13
     brightest
    1.13
     shortest
    1.10
    Activations Density 0.129%

    No Known Activations