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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 235
    Prev
    Next
    INDEX
    Explanations

    dates in month-day-year format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    430
    +0.14
    0.7%
    55
    +0.12
    0.5%
    325
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.10
    55
    +0.12
    0.08
    306
    +0.10
    0.07
    Negative Logits
    ldon
    -0.64
     wasteland
    -0.63
    ioned
    -0.60
     seam
    -0.56
     bom
    -0.54
     plat
    -0.54
     chancellor
    -0.54
     roar
    -0.54
    opic
    -0.53
    natureconservancy
    -0.53
    POSITIVE LOGITS
     2017
    1.52
     2015
    1.47
     2018
    1.45
     2014
    1.44
     2016
    1.43
     2013
    1.40
     2012
    1.33
     2011
    1.30
     2010
    1.28
     2009
    1.26
    Activations Density 0.687%

    No Known Activations