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. 1234
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling and time

    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
    314
    +0.10
    0.5%
    373
    +0.09
    0.4%
    703
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.10
    0.10
    106
    +0.09
    0.07
    393
    +0.09
    0.10
    Negative Logits
    ongo
    -0.56
     Paste
    -0.54
     CoC
    -0.53
    ELL
    -0.52
     Zone
    -0.49
     Esports
    -0.49
    vine
    -0.48
     Amendments
    -0.48
     advances
    -0.47
    ahime
    -0.47
    POSITIVE LOGITS
     way
    0.89
    ©¶æ
    0.89
    til
    0.87
    */(
    0.78
     mornings
    0.77
    morning
    0.77
    hs
    0.76
     morning
    0.76
     week
    0.72
    ħĭ
    0.69
    Activations Density 1.613%

    No Known Activations