© 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. 15033
    Prev
    Next
    INDEX
    Explanations

    misconceptions or contradictions between perception and the actual truth in political contexts

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    642
    +0.12
    0.5%
    29
    +0.12
    0.5%
    544
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.12
    0.02
    642
    +0.12
    0.02
    312
    +0.11
    0.02
    Negative Logits
    pol
    -0.71
    ervative
    -0.63
    inant
    -0.60
     knees
    -0.58
     fever
    -0.57
    etary
    -0.56
    heed
    -0.56
    itialized
    -0.56
    called
    -0.55
    mented
    -0.55
    POSITIVE LOGITS
    Downloadha
    0.74
     {:
    0.70
    é¾įå
    0.69
    é¾į
    0.66
     neither
    0.62
    ãĥł
    0.61
    ÃŁ
    0.60
    >>>>>>>>
    0.60
     contradicts
    0.60
    SPONSORED
    0.59
    Activations Density 0.047%

    No Known Activations