© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal dynamics and human rights issues

    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
    656
    +0.12
    0.6%
    735
    +0.12
    0.5%
    762
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.09
    146
    +0.12
    0.06
    735
    +0.12
    0.05
    Negative Logits
    Shares
    -0.77
    atha
    -0.67
     Sabha
    -0.67
     Latvia
    -0.66
    Lv
    -0.65
    achusetts
    -0.64
    BSD
    -0.64
     Estonia
    -0.64
    rencies
    -0.64
    forums
    -0.63
    POSITIVE LOGITS
     intervention
    1.08
     intervene
    1.01
     intervened
    0.99
     bulldo
    0.98
     forb
    0.91
     swoop
    0.88
     coax
    0.87
     intervening
    0.86
     encro
    0.86
     interventions
    0.85
    Activations Density 0.720%

    No Known Activations