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. 1206
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    393
    +0.16
    0.7%
    385
    +0.12
    0.6%
    561
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.08
    469
    +0.12
    0.06
    561
    +0.12
    0.07
    Negative Logits
    ibe
    -0.77
    uca
    -0.74
    ļéĨĴ
    -0.69
    dad
    -0.68
     thereof
    -0.67
    orporated
    -0.66
    akedown
    -0.65
    riber
    -0.65
    xtap
    -0.65
    ilyn
    -0.64
    POSITIVE LOGITS
     sorts
    1.21
     acron
    0.89
     goodies
    0.88
     events
    0.85
     accomplishments
    0.83
     disparate
    0.77
     adject
    0.77
     posts
    0.76
     grievances
    0.73
     seats
    0.72
    Activations Density 0.787%

    No Known Activations