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 768
    5. 8-RES_FS768-JB
    6. 461
    Prev
    Next
    INDEX
    Explanations

    past events or situations relating to people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    +0.16
    0.7%
    699
    +0.12
    0.6%
    718
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.16
    0.20
    55
    +0.12
    0.21
    102
    +0.12
    0.19
    Negative Logits
    arta
    -0.70
    ethy
    -0.65
     Piercing
    -0.64
     Current
    -0.64
     Extend
    -0.63
     newsletters
    -0.62
     [+]
    -0.60
     Compare
    -0.60
     Mountains
    -0.59
     HAVE
    -0.59
    POSITIVE LOGITS
     originally
    1.28
    hes
    1.27
    wolves
    1.15
     initially
    1.12
    wolf
    1.01
     instrumental
    1.01
     born
    1.00
     conceived
    0.98
     unsuccessful
    0.96
     previously
    0.91
    Activations Density 3.329%

    No Known Activations