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. 11947
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, in this case, "Burke"

    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
    420
    +0.14
    0.6%
    447
    +0.14
    0.6%
    465
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    326
    +0.14
    0.02
    288
    +0.10
    0.02
    Negative Logits
    urgy
    -0.76
    strip
    -0.74
    ebted
    -0.72
    matic
    -0.69
    bread
    -0.68
    outh
    -0.67
    stration
    -0.67
    atural
    -0.67
    ocrine
    -0.66
    atics
    -0.65
    POSITIVE LOGITS
    atana
    0.71
    pload
    0.67
    sonian
    0.65
    BLIC
    0.64
    resses
    0.64
     Fei
    0.62
    yer
    0.62
    aii
    0.61
    ç·
    0.60
     acknow
    0.59
    Activations Density 0.049%

    No Known Activations