© 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. 1-RES-JB
    11. 21241
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nu" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "nu" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.97
    HCR
    -0.76
    âķIJâķIJ
    -0.75
     Crus
    -0.72
    manship
    -0.71
    */(
    -0.69
    âĶģ
    -0.69
    Edited
    -0.68
     hypot
    -0.66
    è¦ļéĨĴ
    -0.66
    POSITIVE LOGITS
     nu
    1.29
    isance
    1.15
    nu
    0.96
    ught
    0.89
     Nu
    0.89
    aband
    0.81
    omin
    0.81
    utonium
    0.79
    awei
    0.78
    isco
    0.78
    Activations Density 0.010%

    No Known Activations