© 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. 39738
    Prev
    Next
    INDEX
    Explanations

    instances of words related to obedience and disobedience to authority figures

    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
    97
    +0.10
    0.5%
    447
    +0.10
    0.5%
    301
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.10
    0.19
    138
    +0.10
    0.16
    316
    +0.10
    0.09
    Negative Logits
    iser
    -0.71
     Fargo
    -0.70
    ivities
    -0.62
    izations
    -0.61
    ouf
    -0.60
    agne
    -0.59
    rine
    -0.59
    adium
    -0.57
    ewater
    -0.57
    oan
    -0.56
    POSITIVE LOGITS
    edient
    0.99
     obedience
    0.96
     obe
    0.90
    edience
    0.84
     obey
    0.79
     disob
    0.78
     obedient
    0.77
    paio
    0.69
     disobedience
    0.69
    ĪĴ
    0.68
    Activations Density 13.233%

    No Known Activations