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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 351
    Prev
    Next
    INDEX
    Explanations

    mentions of colors and nationalities

    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
    289
    +0.14
    0.6%
    760
    +0.12
    0.6%
    425
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.14
    0.04
    537
    +0.12
    0.09
    284
    +0.11
    0.07
    Negative Logits
    izarre
    -0.76
    hran
    -0.71
    bably
    -0.66
    taker
    -0.66
    ETHOD
    -0.65
    BIL
    -0.65
    SPONSORED
    -0.64
    :{
    -0.63
    sonian
    -0.63
     conclud
    -0.63
    POSITIVE LOGITS
    oxide
    1.08
    ioxide
    1.07
    washed
    0.76
     Grass
    0.71
     Metallic
    0.70
    oak
    0.70
    colored
    0.69
    stice
    0.69
    Ń·
    0.69
    thur
    0.69
    Activations Density 2.161%

    No Known Activations