© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24470
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political protests against perceived injustices

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    192
    +0.10
    0.5%
    516
    +0.10
    0.5%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.10
    0.05
    600
    +0.10
    0.03
    25
    +0.10
    0.03
    Negative Logits
    staking
    -0.85
     Canaver
    -0.83
     pouch
    -0.70
     estimating
    -0.67
     Paddock
    -0.67
     largeDownload
    -0.65
     Poker
    -0.65
    emonium
    -0.65
     anecd
    -0.64
     chuck
    -0.64
    POSITIVE LOGITS
     injust
    1.47
     injustice
    1.26
     oppression
    1.15
     evils
    1.06
     bigotry
    1.06
     oppress
    1.04
     tyranny
    1.04
     unjust
    1.04
     atrocities
    1.01
     ideologies
    0.99
    Activations Density 0.572%

    No Known Activations