© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    phrases related to football transfers

    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
    493
    +0.15
    0.7%
    373
    +0.12
    0.6%
    645
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.15
    0.06
    665
    +0.12
    0.05
    451
    +0.10
    0.03
    Negative Logits
    colored
    -0.86
     PBS
    -0.79
     polarization
    -0.79
    GOP
    -0.77
     Navajo
    -0.76
     precincts
    -0.75
    NPR
    -0.75
    CNN
    -0.75
     Tribal
    -0.75
     Cherokee
    -0.74
    POSITIVE LOGITS
     £
    1.45
     âĤ¬
    1.26
     enqu
    1.26
     footballer
    1.25
    £
    1.23
     (£
    1.23
     rumours
    1.18
     Newcastle
    1.16
    iverpool
    1.15
     striker
    1.13
    Activations Density 0.426%

    No Known Activations