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. 1334
    Prev
    Next
    INDEX
    Explanations

    religious references and locations

    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
    384
    +0.15
    0.7%
    393
    +0.15
    0.7%
    379
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.15
    0.13
    393
    +0.15
    0.14
    120
    +0.11
    0.11
    Negative Logits
    imbabwe
    -0.83
    west
    -0.79
    ONSORED
    -0.77
    eland
    -0.76
    KEN
    -0.76
    West
    -0.75
    uca
    -0.74
    ukong
    -0.73
    utan
    -0.73
    aterasu
    -0.73
    POSITIVE LOGITS
     accessories
    1.01
     installations
    1.00
     workshops
    0.99
     decorations
    0.98
     tools
    0.97
     magazines
    0.96
     frameworks
    0.96
     attachments
    0.95
     libraries
    0.95
     personalities
    0.95
    Activations Density 2.024%

    No Known Activations