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 24576
    5. 8-RES_FS24576-JB
    6. 23050
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases related to conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    311
    +0.11
    0.5%
    514
    +0.11
    0.5%
    641
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.11
    0.02
    311
    +0.11
    0.01
    747
    +0.10
    0.02
    Negative Logits
    vez
    -0.76
    ngth
    -0.69
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.64
    FTWARE
    -0.62
    âĸ¬
    -0.62
    âĶģ
    -0.61
     mosa
    -0.60
     contrace
    -0.60
     flux
    -0.59
    CHO
    -0.58
    POSITIVE LOGITS
    ornia
    1.36
    orce
    1.05
    amily
    0.98
    ield
    0.97
    rame
    0.95
    ftime
    0.93
    unction
    0.90
    acet
    0.87
    terness
    0.87
    riend
    0.86
    Activations Density 0.027%

    No Known Activations