© 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 3072
    9. 8-RES_FS3072-JB
    11. 48
    Prev
    Next
    INDEX
    Explanations

    terms related to events involving legal issues, court proceedings, law enforcement, and political activities

    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
    373
    +0.15
    0.7%
    626
    +0.13
    0.6%
    25
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.15
    0.07
    628
    +0.13
    0.07
    626
    +0.11
    0.05
    Negative Logits
     Wikimedia
    -0.77
    Pg
    -0.70
    ãĥ¡
    -0.65
    gra
    -0.60
    ITED
    -0.59
    ibal
    -0.58
    hift
    -0.57
     edit
    -0.56
     Cla
    -0.53
     Chau
    -0.53
    POSITIVE LOGITS
    DERR
    0.83
     beforehand
    0.81
     orally
    0.76
     goodbye
    0.75
     why
    0.75
    è¦ļéĨĴ
    0.72
     how
    0.72
     afterward
    0.70
     via
    0.69
     bluntly
    0.69
    Activations Density 1.368%

    No Known Activations