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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19340
    Prev
    Next
    INDEX
    Explanations

    personal experiences or reflections

    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
    566
    +0.14
    0.7%
    551
    +0.12
    0.5%
    354
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.05
    551
    +0.12
    0.05
    502
    +0.12
    0.04
    Negative Logits
    lation
    -0.75
    geon
    -0.73
    mund
    -0.69
    ardless
    -0.67
    math
    -0.64
    Dom
    -0.62
     srfAttach
    -0.62
    reality
    -0.61
    plant
    -0.60
     Wem
    -0.60
    POSITIVE LOGITS
     learnt
    0.99
     learned
    0.98
     wish
    0.98
     Learned
    0.90
     bucket
    0.84
     wanted
    0.81
     noticed
    0.80
     wished
    0.79
     dislike
    0.79
     forgot
    0.77
    Activations Density 0.111%

    No Known Activations