© 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 24576
    9. 8-RES_FS24576-JB
    11. 12052
    Prev
    Next
    INDEX
    Explanations

    information related to legal issues and court proceedings, along with mentions of intelligence organizations and speculation on spy activities

    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
    146
    +0.14
    0.6%
    388
    +0.10
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.14
    0.04
    388
    +0.10
    0.03
    179
    +0.09
    0.03
    Negative Logits
     srfAttach
    -0.70
    church
    -0.67
    feat
    -0.67
    rise
    -0.66
     dehyd
    -0.64
     wart
    -0.64
    obyl
    -0.63
    Church
    -0.61
     lyr
    -0.61
     epoch
    -0.60
    POSITIVE LOGITS
     Inspect
    1.01
     inspector
    0.97
     tasked
    0.96
     Accountability
    0.95
     discretion
    0.95
     investigating
    0.94
     Commissioners
    0.92
    artments
    0.92
     Officers
    0.92
     Regulation
    0.91
    Activations Density 0.129%

    No Known Activations