© 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. 16730
    Prev
    Next
    INDEX
    Explanations

    political entities and related activities, such as politicians, political parties and their actions

    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
    480
    +0.49
    2.5%
    87
    +0.15
    0.8%
    266
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.03
    266
    +0.15
    0.10
    31
    +0.15
    0.08
    Negative Logits
     fortun
    -0.64
     experien
    -0.62
     attribution
    -0.62
     converter
    -0.61
     voy
    -0.60
     genetics
    -0.58
     metab
    -0.57
     primitive
    -0.56
     rhy
    -0.55
     liner
    -0.54
    POSITIVE LOGITS
    Senate
    1.29
     Senate
    1.22
     senators
    1.15
    Republicans
    1.14
    Democrats
    1.13
    Senator
    1.12
     Vote
    1.10
     senate
    1.10
     Democrats
    1.10
     caucus
    1.08
    Activations Density 1.339%

    No Known Activations