© 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 Local
    9. 6-RES_SCL-AJT
    11. 32118
    Prev
    Next
    INDEX
    Explanations

    phrases related to military equipment and operations

    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
    +0.21
    0.9%
    578
    +0.12
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.21
    0.11
    578
    +0.12
    0.05
    664
    +0.11
    0.08
    Negative Logits
     contrace
    -0.72
     interven
    -0.68
     biod
    -0.65
     treaties
    -0.64
     perce
    -0.64
     reconcil
    -0.63
     [|
    -0.62
    ¥µ
    -0.61
    ©¶æ
    -0.61
     calming
    -0.61
    POSITIVE LOGITS
    matter
    1.02
    itute
    1.02
    chens
    0.98
    gerald
    0.98
    creen
    0.95
    terness
    0.90
    ters
    0.89
    airs
    0.88
    itution
    0.85
    weet
    0.84
    Activations Density 9.930%

    No Known Activations