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

    Neuronpedia

    Jacobian LensNEW
    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. 22195
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between elements in a system

    oai_token-act-pair · gpt-4o-miniTriggered 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
    333
    +0.12
    0.6%
    80
    +0.11
    0.5%
    660
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.12
    0.02
    660
    +0.11
    0.02
    80
    +0.10
    0.02
    Negative Logits
    çīĪ
    -0.72
    abase
    -0.70
    romy
    -0.70
     captcha
    -0.66
    igs
    -0.65
    opol
    -0.62
    aways
    -0.61
    opian
    -0.61
    ouver
    -0.60
    izon
    -0.60
    POSITIVE LOGITS
     better
    1.04
     louder
    0.96
     clearer
    0.95
     stronger
    0.93
     healthier
    0.93
     harder
    0.89
     greater
    0.87
    better
    0.87
     less
    0.87
     quicker
    0.86
    Activations Density 0.074%

    No Known Activations