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. 1832
    Prev
    Next
    INDEX
    Explanations

    U.S. state names and universities

    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
    566
    +0.13
    0.6%
    57
    +0.11
    0.5%
    274
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.12
    57
    +0.11
    0.06
    659
    +0.11
    0.07
    Negative Logits
    ly
    -1.01
    iture
    -0.93
    itional
    -0.81
    ãĥ¼ãĥĨãĤ£
    -0.81
    atu
    -0.80
    sonian
    -0.80
    HCR
    -0.79
    */(
    -0.79
    elong
    -0.78
    ãĥ¼ãĥĨ
    -0.77
    POSITIVE LOGITS
     Candle
    0.83
    APH
    0.74
     Prophe
    0.70
     Apostles
    0.69
     Buc
    0.68
    650
    0.67
    GAN
    0.62
    Lens
    0.62
     Hook
    0.60
     apostles
    0.60
    Activations Density 1.639%

    No Known Activations