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. 224
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and power

    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
    218
    +0.11
    0.5%
    756
    +0.10
    0.4%
    625
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.14
    125
    +0.10
    0.07
    575
    +0.09
    0.10
    Negative Logits
    enegger
    -0.79
    ruary
    -0.68
    Recommend
    -0.66
    onic
    -0.66
    jen
    -0.63
    tein
    -0.62
    soon
    -0.61
    uni
    -0.61
    lyn
    -0.60
    asus
    -0.60
    POSITIVE LOGITS
    eering
    1.05
    ership
    1.03
    eers
    0.89
    orship
    0.83
     levers
    0.83
     controlled
    0.82
    rador
    0.78
    eer
    0.78
    taker
    0.77
    rollers
    0.77
    Activations Density 2.764%

    No Known Activations