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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12303
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements between parties

    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
    224
    +0.14
    0.7%
    447
    +0.14
    0.6%
    679
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.03
    224
    +0.14
    0.03
    575
    +0.13
    0.03
    Negative Logits
    asus
    -0.90
    crow
    -0.80
     darts
    -0.70
    gun
    -0.69
    pse
    -0.68
    culus
    -0.68
    ãĥ©ãĥ³
    -0.67
    vas
    -0.67
    stocks
    -0.67
    dden
    -0.66
    POSITIVE LOGITS
     agreements
    1.13
     agreement
    1.12
     negotiated
    1.10
    reements
    1.10
     Agreement
    1.07
    ually
    1.00
     treaties
    0.96
     treaty
    0.95
     signed
    0.90
    reement
    0.89
    Activations Density 0.049%

    No Known Activations