© 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 49152
    9. 8-RES_FS49152-JB
    11. 26821
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and their roles in security and immigration enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    100
    +0.10
    0.5%
    627
    +0.10
    0.5%
    159
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.10
    0.03
    385
    +0.10
    0.03
    534
    +0.08
    0.02
    Negative Logits
     poems
    -0.90
     fantasies
    -0.88
     selfies
    -0.83
     kittens
    -0.82
     demos
    -0.82
     blasp
    -0.81
     upside
    -0.79
     tales
    -0.78
     illusions
    -0.76
     dreams
    -0.75
    POSITIVE LOGITS
     Department
    1.47
    Department
    1.33
    gov
    1.29
    Office
    1.29
     Dept
    1.25
     Office
    1.25
     department
    1.25
     Bureau
    1.24
     Directorate
    1.24
     DHS
    1.21
    Activations Density 0.168%

    No Known Activations