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 1536
    5. 8-RES_FS1536-JB
    6. 1527
    Prev
    Next
    INDEX
    Explanations

    references to events occurring in a certain time frame involving a certain entity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.13
    0.6%
    745
    +0.10
    0.5%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.13
    476
    +0.10
    0.06
    127
    +0.10
    0.06
    Negative Logits
    uala
    -0.86
    fy
    -0.73
    behind
    -0.70
    uminati
    -0.63
    thood
    -0.63
    pelling
    -0.63
    vu
    -0.63
    VW
    -0.62
    vana
    -0.61
    istry
    -0.60
    POSITIVE LOGITS
     weekend
    0.94
     span
    0.94
     course
    0.90
     horizon
    0.89
     holidays
    0.81
     threshold
    0.80
     whole
    0.80
     fence
    0.80
     millennia
    0.78
     objections
    0.78
    Activations Density 1.660%

    No Known Activations