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. 781
    Prev
    Next
    INDEX
    Explanations

    technical terms and information related to software development and health conditions

    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
    718
    +0.11
    0.5%
    68
    +0.11
    0.5%
    445
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.13
    326
    +0.11
    0.14
    288
    +0.11
    0.16
    Negative Logits
    itsch
    -0.68
     Jenner
    -0.65
    INGTON
    -0.64
     secrecy
    -0.62
    enburg
    -0.62
    uminati
    -0.61
    orate
    -0.60
    iard
    -0.59
    shire
    -0.59
     NCT
    -0.58
    POSITIVE LOGITS
    plings
    0.90
    geant
    0.88
    eways
    0.87
    pling
    0.85
    addle
    0.84
    avage
    0.84
    apore
    0.82
    udo
    0.81
    arin
    0.79
    ority
    0.78
    Activations Density 2.982%

    No Known Activations