© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2664
    Prev
    Next
    INDEX
    Explanations

    mentions of foreign relations or diplomatic activities between different countries

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    169
    +0.15
    0.6%
    2
    +0.14
    0.5%
    348
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.15
    574
    +0.14
    0.07
    496
    +0.13
    0.12
    Negative Logits
    olson
    -0.93
    igraph
    -0.83
     curl
    -0.83
    ounter
    -0.83
    rawdownloadcloneembedreportprint
    -0.81
    ouses
    -0.80
     recite
    -0.79
    ersion
    -0.78
     pear
    -0.78
    ilty
    -0.78
    POSITIVE LOGITS
     Authority
    1.37
     Accountability
    1.29
     Affairs
    1.28
     Bureau
    1.26
     Department
    1.22
     Commission
    1.20
     Commissioner
    1.20
     Aid
    1.16
     Council
    1.15
     Enforcement
    1.14
    Activations Density 1.706%

    No Known Activations