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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13675
    Prev
    Next
    INDEX
    Explanations

    the word 'normal' occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "normal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lein
    -0.75
     Designs
    -0.71
    among
    -0.66
    osures
    -0.65
    otle
    -0.65
    lege
    -0.64
    kar
    -0.64
     cites
    -0.63
    holders
    -0.63
     ðŁij
    -0.62
    POSITIVE LOGITS
     normal
    3.60
    normal
    2.95
    Normal
    2.28
     Normal
    2.18
     usual
    1.98
     ordinary
    1.92
     norm
    1.87
     normalized
    1.76
     regular
    1.72
     typical
    1.62
    Activations Density 0.016%

    No Known Activations