© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    the word "normal" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the word "normal" and its various contexts related to societal standards and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    better
    -0.74
    hani
    -0.70
    artisan
    -0.68
    leted
    -0.66
    raped
    -0.64
    Sov
    -0.64
    intel
    -0.63
    resent
    -0.62
    hung
    -0.61
    Winged
    -0.61
    POSITIVE LOGITS
    cy
    1.50
    ization
    1.44
    izing
    1.40
    isation
    1.35
    ised
    1.34
    izes
    1.30
    ize
    1.23
    ising
    1.21
    ized
    1.19
    izations
    1.12
    Activations Density 0.044%

    No Known Activations