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. 1718
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of 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
    362
    +0.12
    0.5%
    640
    +0.10
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.07
    636
    +0.10
    0.04
    269
    +0.10
    0.04
    Negative Logits
    uala
    -0.74
    UA
    -0.67
    vu
    -0.66
    vana
    -0.64
     Squadron
    -0.63
    behind
    -0.63
    ulhu
    -0.63
    vp
    -0.61
    Behind
    -0.60
    fy
    -0.60
    POSITIVE LOGITS
     weekend
    1.03
     course
    1.00
     span
    0.98
     millennia
    0.96
     centuries
    0.91
    hang
    0.88
     decades
    0.86
     years
    0.83
     holidays
    0.81
     hump
    0.81
    Activations Density 0.518%

    No Known Activations