© 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. 13087
    Prev
    Next
    INDEX
    Explanations

    words related to military activities and conflict

    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
    314
    +0.14
    0.5%
    659
    +0.14
    0.5%
    205
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.13
    314
    +0.14
    -0.06
    556
    +0.13
    0.10
    Negative Logits
     glim
    -0.90
    itiveness
    -0.88
    sels
    -0.85
    glers
    -0.77
    urally
    -0.74
     PV
    -0.73
    initialized
    -0.71
     promoters
    -0.71
    hift
    -0.70
    retty
    -0.70
    POSITIVE LOGITS
    azeera
    1.36
    querque
    1.07
    aeda
    1.06
    ibrary
    1.01
    hyde
    1.00
    aida
    1.00
    arez
    0.95
    ĸļ
    0.93
    abi
    0.91
    aghd
    0.88
    Activations Density 11.944%

    No Known Activations