© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34914
    Prev
    Next
    INDEX
    Explanations

    references to Chinese-related entities or topics

    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
    447
    +0.18
    0.8%
    267
    +0.12
    0.5%
    96
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.18
    0.02
    635
    +0.12
    0.06
    450
    +0.11
    0.07
    Negative Logits
    olkien
    -0.89
    utherford
    -0.86
    mble
    -0.81
    gger
    -0.81
    ively
    -0.81
    odder
    -0.81
    aird
    -0.80
    lain
    -0.79
    aucus
    -0.79
     Byr
    -0.79
    POSITIVE LOGITS
     nationals
    1.03
     yuan
    0.91
     communists
    0.87
     Yuan
    0.84
     Communists
    0.84
     Yen
    0.83
     Communist
    0.82
     immigrants
    0.81
     nationalists
    0.80
     mainland
    0.77
    Activations Density 11.303%

    No Known Activations