© 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. 35374
    Prev
    Next
    INDEX
    Explanations

    phrases related to military service and duty

    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
    +0.17
    0.7%
    288
    +0.15
    0.7%
    247
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.17
    247
    +0.15
    0.07
    111
    +0.12
    0.07
    Negative Logits
    romeda
    -0.78
    ongyang
    -0.71
    izon
    -0.67
    monary
    -0.65
    Stage
    -0.63
     Seeds
    -0.62
     fertile
    -0.62
    Origin
    -0.62
     Bloom
    -0.61
     suspic
    -0.60
    POSITIVE LOGITS
    service
    0.82
    hire
    0.81
     Employees
    0.80
     acad
    0.78
    ful
    0.77
    able
    0.77
    manship
    0.76
     rendered
    0.76
    istry
    0.74
    irmation
    0.74
    Activations Density 5.932%

    No Known Activations