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 3072
    5. 8-RES_FS3072-JB
    6. 934
    Prev
    Next
    INDEX
    Explanations

    mentions of materials or plants

    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
    447
    +0.29
    1.4%
    481
    +0.24
    1.1%
    468
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.20
    481
    +0.24
    0.16
    575
    +0.10
    0.14
    Negative Logits
     Cum
    -0.66
    Detailed
    -0.65
     Coastal
    -0.64
    awar
    -0.62
     Hyundai
    -0.62
     Pharm
    -0.62
    Mp
    -0.62
     Ballistic
    -0.60
     Adren
    -0.58
    Tes
    -0.57
    POSITIVE LOGITS
     altogether
    0.75
     etiquette
    0.72
     outweigh
    0.68
     enabled
    0.68
    ipedia
    0.67
     oneself
    0.67
     pronouns
    0.67
     everywhere
    0.66
     abroad
    0.66
     cubes
    0.65
    Activations Density 2.938%

    No Known Activations