© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12392
    Prev
    Next
    INDEX
    Explanations

    terms related to the conflict in Yemen, particularly mentioning the Houthi rebels and various locations within Yemen like Aden, Sana'a, and Taiz

    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
    508
    +0.13
    0.5%
    575
    +0.13
    0.5%
    322
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.14
    288
    +0.13
    0.16
    48
    +0.12
    0.10
    Negative Logits
    âķIJâķIJ
    -1.06
    ãĤ´ãĥ³
    -0.96
    ument
    -0.95
    使
    -0.88
    -+-+-+-+
    -0.86
    ainer
    -0.85
    ãĥĥãĥĪ
    -0.82
    antly
    -0.79
    ablishment
    -0.79
    reet
    -0.78
    POSITIVE LOGITS
    ilant
    1.12
    ilee
    1.00
    itism
    0.96
    ilitation
    0.94
    haus
    0.94
    poons
    0.94
    marked
    0.91
    EStream
    0.90
    accompan
    0.90
    cffff
    0.89
    Activations Density 2.684%

    No Known Activations