Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1154
    Prev
    Next
    INDEX
    Explanations

    educational institutions and related activities

    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
    679
    +0.13
    0.6%
    258
    +0.13
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.15
    537
    +0.13
    0.13
    114
    +0.11
    0.11
    Negative Logits
    potion
    -0.79
    CHAT
    -0.73
    tein
    -0.71
    otos
    -0.69
    Accessory
    -0.63
    ultimate
    -0.63
    bush
    -0.60
    proof
    -0.58
    rontal
    -0.57
    Timer
    -0.57
    POSITIVE LOGITS
    hips
    1.43
    chool
    1.17
    hare
    1.10
    paces
    1.08
     alike
    1.05
    ystem
    1.01
     nationwide
    0.99
    folk
    0.98
    hops
    0.97
     vying
    0.97
    Activations Density 1.739%

    No Known Activations