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. 1443
    Prev
    Next
    INDEX
    Explanations

    information related to business agreements and technological advancements

    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
    265
    +0.11
    0.5%
    665
    +0.10
    0.4%
    324
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.11
    0.13
    306
    +0.10
    0.10
    677
    +0.10
    0.09
    Negative Logits
     flourished
    -0.69
     mistakenly
    -0.67
     existed
    -0.65
     wrongly
    -0.64
     differed
    -0.64
     scorn
    -0.64
     lately
    -0.63
     Wrong
    -0.62
    ¬¼
    -0.62
     raged
    -0.61
    POSITIVE LOGITS
     tomorrow
    1.33
     2019
    1.26
    morrow
    1.24
     2021
    1.16
     2020
    1.12
     someday
    1.11
     next
    1.10
    2019
    1.05
     hereafter
    1.01
    soon
    1.00
    Activations Density 2.542%

    No Known Activations