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. 1839
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to activities and observations

    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
    480
    +0.52
    2.6%
    266
    +0.10
    0.5%
    155
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.03
    266
    +0.10
    0.19
    288
    +0.07
    0.18
    Negative Logits
    DonaldTrump
    -0.54
    ibrary
    -0.52
    ©¶æ
    -0.49
     AND
    -0.49
     Category
    -0.45
     looph
    -0.45
     Aval
    -0.44
     and
    -0.44
    and
    -0.43
     Emblem
    -0.42
    POSITIVE LOGITS
     thereof
    1.11
     alike
    1.03
     thereto
    0.99
     thereafter
    0.91
     versa
    0.89
     therein
    0.87
     accordingly
    0.87
     respectively
    0.78
    cellaneous
    0.72
     afterward
    0.67
    Activations Density 4.918%

    No Known Activations