© 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 49152
    9. 8-RES_FS49152-JB
    11. 25995
    Prev
    Next
    INDEX
    Explanations

    terms related to ultraconservative ideologies and groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.11
    0.5%
    575
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.11
    0.01
    539
    +0.11
    0.01
    723
    +0.10
    0.01
    Negative Logits
     guiActiveUnfocused
    -0.71
     Dragonbound
    -0.69
    fulness
    -0.68
    ãģ®éŃĶ
    -0.65
    fully
    -0.65
    âķIJâķIJ
    -0.65
     CLSID
    -0.64
    stocks
    -0.61
    sense
    -0.61
    ELS
    -0.60
    POSITIVE LOGITS
    asonic
    1.23
    acons
    1.07
    adian
    1.00
    entary
    0.92
    atron
    0.90
    aband
    0.90
    adic
    0.90
    inary
    0.89
    agnetic
    0.88
    acet
    0.86
    Activations Density 0.005%

    No Known Activations