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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2823
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    599
    +0.11
    0.5%
    71
    +0.10
    0.5%
    165
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.07
    310
    +0.10
    0.09
    616
    +0.10
    0.08
    Negative Logits
    sonian
    -0.74
    odox
    -0.71
     endif
    -0.66
    olor
    -0.63
    Fight
    -0.62
    Something
    -0.62
    \<
    -0.62
    atom
    -0.61
    asso
    -0.60
    Nothing
    -0.60
    POSITIVE LOGITS
     total
    1.03
     2015
    0.94
     2014
    0.94
     2010
    0.90
     2016
    0.90
     2011
    0.89
     2012
    0.89
     2013
    0.89
     2009
    0.86
    total
    0.86
    Activations Density 2.285%

    No Known Activations