© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3113
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    418
    +0.12
    0.5%
    314
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.12
    0.03
    418
    +0.11
    0.02
    639
    +0.10
    0.02
    Negative Logits
     operating
    -0.75
     incub
    -0.74
     aggregate
    -0.74
     NEXT
    -0.73
     susp
    -0.69
     hiber
    -0.69
     procedural
    -0.68
     procedure
    -0.68
     PRO
    -0.66
     acronym
    -0.66
    POSITIVE LOGITS
    style
    1.22
    chan
    1.21
    sama
    1.20
    kun
    1.17
    san
    1.10
    Jones
    1.08
    Marie
    1.05
    worthy
    1.05
    induced
    1.05
    directed
    1.03
    Activations Density 0.030%

    No Known Activations