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 24576
    5. 8-RES_FS24576-JB
    6. 21928
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and events related to Yemen

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    288
    +0.17
    0.8%
    481
    +0.16
    0.7%
    682
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    682
    +0.17
    0.02
    288
    +0.16
    0.01
    67
    +0.10
    0.01
    Negative Logits
     LAPD
    -0.76
    ablishment
    -0.75
     Lovecraft
    -0.72
    ierrez
    -0.71
    ainer
    -0.71
    âķIJâķIJ
    -0.66
    hent
    -0.64
    ++++++++++++++++
    -0.64
    antly
    -0.63
    ãĤĮ
    -0.62
    POSITIVE LOGITS
    awi
    0.85
    beans
    0.84
    ites
    0.84
    ite
    0.79
    bean
    0.76
    istani
    0.74
     Houth
    0.73
    inia
    0.73
    atar
    0.73
    itic
    0.73
    Activations Density 0.017%

    No Known Activations