© 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 49152
    9. 8-RES_FS49152-JB
    11. 45564
    Prev
    Next
    INDEX
    Explanations

    terms related to societal and political issues, particularly focusing on justice, reform, and systemic challenges

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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.26
    1.2%
    481
    +0.17
    0.8%
    454
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.06
    439
    +0.17
    0.04
    724
    +0.11
    0.05
    Negative Logits
     Brow
    -0.58
     Stab
    -0.56
    laugh
    -0.55
    cise
    -0.55
    hin
    -0.54
     Honour
    -0.54
     Saying
    -0.53
     Coral
    -0.52
    ullivan
    -0.52
     Thanksgiving
    -0.52
    POSITIVE LOGITS
     exists
    1.14
     improves
    1.07
     dominates
    1.03
     tends
    1.02
     occurs
    1.01
     persists
    1.00
     requires
    0.99
     isn
    0.98
     involves
    0.98
     entails
    0.98
    Activations Density 0.176%

    No Known Activations