Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24221
    Prev
    Next
    INDEX
    Explanations

    phrases containing the abbreviation "Nu" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "nu" or its variations, likely related to a specific organization or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.77
    Edited
    -0.70
    */(
    -0.69
    xual
    -0.69
    è¦ļéĨĴ
    -0.68
     Wasteland
    -0.68
     Assass
    -0.67
    haw
    -0.67
     Parables
    -0.65
    âĶģ
    -0.64
    POSITIVE LOGITS
    isance
    1.32
    endo
    1.04
    anced
    0.99
    ptions
    0.92
    pert
    0.88
     Nu
    0.87
    ught
    0.87
    iture
    0.86
    ples
    0.82
    aband
    0.80
    Activations Density 0.025%

    No Known Activations