© 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. 14819
    Prev
    Next
    INDEX
    Explanations

    news related to fundraising efforts for medical causes or financial assistance in the face of adversity

    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
    480
    +0.46
    2.4%
    266
    +0.14
    0.7%
    447
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.46
    0.02
    266
    +0.14
    0.08
    720
    +0.13
    0.06
    Negative Logits
    Attach
    -0.71
    ãĥ´ãĤ¡
    -0.70
     predecessor
    -0.64
    ONSORED
    -0.62
    代
    -0.62
    Insert
    -0.61
    Attributes
    -0.60
    ç«
    -0.58
    åŃ
    -0.56
    âĶĢâĶĢâĶĢâĶĢ
    -0.56
    POSITIVE LOGITS
     rejoice
    0.79
     beware
    0.75
     alike
    0.70
     clam
    0.70
     flock
    0.68
    joice
    0.67
    selves
    0.66
     evacuated
    0.64
     themselves
    0.63
     Beware
    0.61
    Activations Density 0.690%

    No Known Activations