© 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 1536
    9. 8-RES_FS1536-JB
    11. 1160
    Prev
    Next
    INDEX
    Explanations

    mentions of political bills and legislation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    31
    +0.12
    0.5%
    447
    +0.11
    0.5%
    690
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.12
    0.12
    690
    +0.11
    0.09
    13
    +0.11
    0.10
    Negative Logits
     Sul
    -0.70
     Stain
    -0.69
    aspers
    -0.68
     Moor
    -0.67
     Degree
    -0.66
     Sie
    -0.64
     prolet
    -0.64
     wander
    -0.64
    Naz
    -0.64
     Pascal
    -0.64
    POSITIVE LOGITS
     proposals
    1.32
     legislation
    1.28
     repeal
    1.25
     proposal
    1.21
     enacted
    1.18
     repealing
    1.16
     proposed
    1.15
     legisl
    1.10
     legalizing
    1.07
     amend
    1.06
    Activations Density 2.932%

    No Known Activations