© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 17482
    Prev
    Next
    INDEX
    Explanations

    the concept of what is considered normal or normalization in societal, medical, and cultural contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "normalcy" and related discussions on mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    better
    -0.78
    artisan
    -0.68
    leted
    -0.68
    REL
    -0.65
    çīĪ
    -0.63
    rad
    -0.61
    hire
    -0.60
    hani
    -0.60
     wisely
    -0.60
    asus
    -0.59
    POSITIVE LOGITS
    cy
    1.58
    ization
    1.43
    izing
    1.43
    isation
    1.37
    ised
    1.36
    ising
    1.28
    izes
    1.28
    ize
    1.21
    ized
    1.19
    izations
    1.14
    Activations Density 0.067%

    No Known Activations