© 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 3072
    9. 8-RES_FS3072-JB
    11. 3016
    Prev
    Next
    INDEX
    Explanations

    political and international relations-related phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    36
    +0.21
    1.0%
    481
    +0.16
    0.8%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.21
    0.19
    263
    +0.16
    0.11
    730
    +0.12
    0.10
    Negative Logits
    Own
    -0.70
    arsity
    -0.69
    Arcade
    -0.59
    <?
    -0.59
    frames
    -0.59
    powers
    -0.59
    anism
    -0.58
     Mysteries
    -0.58
    pees
    -0.57
    Enjoy
    -0.57
    POSITIVE LOGITS
    cknowled
    1.31
     spokesperson
    1.15
     spokeswoman
    1.11
     spokesman
    1.07
    cknow
    1.05
    usterity
    1.04
    ctors
    0.98
    verages
    0.96
    lyss
    0.96
     couple
    0.94
    Activations Density 0.811%

    No Known Activations