Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21483
    Prev
    Next
    INDEX
    Explanations

    political references and discussions

    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
    283
    +0.15
    0.7%
    526
    +0.12
    0.6%
    228
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.15
    -0.00
    283
    +0.12
    0.02
    350
    +0.10
    0.05
    Negative Logits
    iple
    -0.81
     Variant
    -0.80
    initely
    -0.74
    sterdam
    -0.72
     NAD
    -0.71
     FANTASY
    -0.70
     Detect
    -0.69
     Guinness
    -0.69
     Libraries
    -0.65
     explorers
    -0.64
    POSITIVE LOGITS
     ideologically
    1.13
     unpopular
    1.10
    Republicans
    1.10
    Democrats
    1.09
     voters
    1.09
     GOP
    1.07
     electoral
    1.07
     politically
    1.06
     partisan
    1.05
     centrist
    1.05
    Activations Density 0.920%

    No Known Activations