© 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 24576
    9. 8-RES_FS24576-JB
    11. 18470
    Prev
    Next
    INDEX
    Explanations

    mentions of "The Huffington Post."

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    267
    +0.11
    0.5%
    474
    +0.10
    0.5%
    475
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.11
    0.03
    267
    +0.10
    0.02
    547
    +0.10
    0.02
    Negative Logits
     tide
    -0.84
    ardless
    -0.74
    ģĸ
    -0.68
     drain
    -0.67
     blinded
    -0.67
     fortun
    -0.66
     puls
    -0.64
     rall
    -0.63
     dil
    -0.63
    sei
    -0.63
    POSITIVE LOGITS
     Publishing
    0.89
     Magazine
    0.88
     Digest
    0.86
     LLP
    0.85
    lished
    0.84
     Presents
    0.83
    Leaks
    0.82
     editors
    0.80
     Marketplace
    0.79
     editor
    0.79
    Activations Density 0.036%

    No Known Activations