Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 390
    Prev
    Next
    INDEX
    Explanations

    places and names related to political events or international disputes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    683
    +0.11
    0.5%
    373
    +0.11
    0.5%
    386
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.06
    103
    +0.11
    0.08
    232
    +0.11
    0.08
    Negative Logits
    imore
    -0.77
    aroo
    -0.76
    ruary
    -0.74
    quished
    -0.69
    >>\
    -0.65
     Pigs
    -0.63
    birth
    -0.61
    rules
    -0.61
     Engels
    -0.59
    yrim
    -0.58
    POSITIVE LOGITS
    ãĤ£
    0.69
    ĸļ
    0.64
    ecast
    0.61
    inki
    0.60
    Marie
    0.59
     Cth
    0.58
    ciating
    0.56
    ilo
    0.56
    ibur
    0.56
    uku
    0.56
    Activations Density 2.010%

    No Known Activations