© 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 24576
    9. 8-RES_FS24576-JB
    11. 7671
    Prev
    Next
    INDEX
    Explanations

    information related to political figures or polling statistics

    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
    +0.47
    2.4%
    266
    +0.10
    0.5%
    658
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    -0.00
    668
    +0.10
    0.04
    566
    +0.09
    0.05
    Negative Logits
     oneself
    -0.65
     Yourself
    -0.56
    Rew
    -0.56
    ifestyle
    -0.56
     concludes
    -0.53
    externalActionCode
    -0.53
    clusive
    -0.52
     identities
    -0.51
    wealth
    -0.50
    collect
    -0.49
    POSITIVE LOGITS
     likewise
    1.02
     similarly
    0.92
     meanwhile
    0.90
     theirs
    0.67
     Same
    0.63
     unaffected
    0.61
     similar
    0.60
     chim
    0.60
     hers
    0.55
     pts
    0.52
    Activations Density 1.011%

    No Known Activations