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 6144
    5. 8-RES_FS6144-JB
    6. 4571
    Prev
    Next
    INDEX
    Explanations

    geopolitical and socio-economic terms, especially related to countries and regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    481
    +0.15
    0.7%
    408
    +0.12
    0.6%
    425
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.15
    0.06
    43
    +0.12
    0.05
    425
    +0.12
    0.06
    Negative Logits
    Ķ
    -0.69
    apult
    -0.67
    iously
    -0.67
    ibe
    -0.66
    ãĤ´ãĥ³
    -0.66
    rolet
    -0.65
    è¦ļéĨĴ
    -0.65
    Cause
    -0.64
    SI
    -0.63
    igan
    -0.63
    POSITIVE LOGITS
     however
    1.09
     meanwhile
    1.08
     moreover
    0.90
     there
    0.90
     where
    0.88
    there
    0.83
    where
    0.82
     we
    0.79
     wherein
    0.66
     birthplace
    0.64
    Activations Density 0.564%

    No Known Activations