© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8691
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or situations, particularly those involving descriptions and events

    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
    584
    +0.11
    0.5%
    190
    +0.10
    0.5%
    300
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.11
    0.06
    390
    +0.10
    0.05
    584
    +0.10
    0.06
    Negative Logits
    burgh
    -0.71
    RESULTS
    -0.65
    talk
    -0.62
    cot
    -0.59
     Doctrine
    -0.59
     Chiefs
    -0.58
    Forest
    -0.56
    inventoryQuantity
    -0.55
    akings
    -0.55
    Quote
    -0.55
    POSITIVE LOGITS
     solely
    0.90
     by
    0.85
     exclusively
    0.83
     BY
    0.79
    ¥ŀ
    0.77
     prominently
    0.76
     jointly
    0.71
     chiefly
    0.69
    itled
    0.68
     loosely
    0.67
    Activations Density 0.225%

    No Known Activations