© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16773
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Nu" followed by a number, potentially related to specific events or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "nu" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.90
    Edited
    -0.80
    Reviewed
    -0.69
     Crus
    -0.69
    è¦ļéĨĴ
    -0.68
    anooga
    -0.67
    HCR
    -0.67
    Introduced
    -0.67
    */(
    -0.66
    âķIJâķIJ
    -0.66
    POSITIVE LOGITS
    isance
    1.15
     nu
    0.96
    endo
    0.92
    iture
    0.87
    estro
    0.86
    anced
    0.85
    ptions
    0.85
    ZZ
    0.84
    ught
    0.82
    awei
    0.80
    Activations Density 0.008%

    No Known Activations