© 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 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. 43479
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative processes and healthcare policy reform

    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
    373
    +0.20
    0.9%
    161
    +0.10
    0.5%
    482
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.20
    0.03
    482
    +0.10
    0.03
    688
    +0.10
    0.03
    Negative Logits
     Tiff
    -0.75
     realised
    -0.74
     realise
    -0.74
     learnt
    -0.73
     Tend
    -0.73
     Dh
    -0.72
     DJs
    -0.71
    Sensor
    -0.70
     keen
    -0.68
     terr
    -0.68
    POSITIVE LOGITS
     ObamaCare
    1.24
    amacare
    1.22
     Obamacare
    1.17
     repeal
    1.13
    Senate
    1.09
     filibuster
    1.08
     appropriations
    1.06
    Congress
    1.05
     congressional
    1.02
     defund
    1.01
    Activations Density 0.163%

    No Known Activations