© 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. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 5052
    Prev
    Next
    INDEX
    Explanations

    topics related to geopolitical tensions and diplomatic relationships, especially in the South China Sea

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    378
    +0.11
    0.5%
    616
    +0.11
    0.5%
    211
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.09
    662
    +0.11
    0.11
    211
    +0.10
    -0.03
    Negative Logits
    RM
    -0.71
    erity
    -0.66
    MSN
    -0.65
    PDATE
    -0.64
    berman
    -0.63
    report
    -0.63
    playing
    -0.62
    elson
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
    iquette
    -0.60
    POSITIVE LOGITS
     Lumpur
    0.72
     Sea
    0.65
     Sadd
    0.63
     enclave
    0.62
     separatist
    0.62
     plateau
    0.62
    ersed
    0.59
     Extensions
    0.58
     valleys
    0.56
    atan
    0.55
    Activations Density 11.011%

    No Known Activations