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. 1505
    Prev
    Next
    INDEX
    Explanations

    terms related to video games and technology

    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
    41
    +0.10
    0.5%
    615
    +0.10
    0.4%
    712
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.24
    575
    +0.10
    0.17
    537
    +0.09
    0.15
    Negative Logits
    à¨
    -0.72
    å§«
    -0.61
    é¾įå
    -0.60
     Presbyterian
    -0.60
     Brow
    -0.59
    yss
    -0.59
    xious
    -0.59
    theless
    -0.59
    itious
    -0.58
    imil
    -0.58
    POSITIVE LOGITS
    ilogy
    0.85
    undrum
    0.78
    naire
    0.76
    astery
    0.74
    posium
    0.71
     kit
    0.69
    stros
    0.69
    lance
    0.69
    owder
    0.68
    reciation
    0.67
    Activations Density 4.889%

    No Known Activations