© 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. 34889
    Prev
    Next
    INDEX
    Explanations

    keywords related to rules, regulations, and guidelines, especially in the context of governance, military operations, and decision-making processes

    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
    738
    +0.11
    0.5%
    735
    +0.11
    0.5%
    509
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.11
    0.18
    255
    +0.11
    0.09
    125
    +0.11
    0.07
    Negative Logits
    Jr
    -0.79
     Mour
    -0.75
    naissance
    -0.75
    ovies
    -0.74
     Idea
    -0.72
    ovember
    -0.71
    undreds
    -0.71
    culus
    -0.70
    anian
    -0.69
    illions
    -0.69
    POSITIVE LOGITS
     governing
    0.89
     governs
    0.89
     pertaining
    0.86
     applicable
    0.82
    glers
    0.81
     promulg
    0.81
     regulations
    0.79
     rules
    0.76
     regulating
    0.76
     apply
    0.76
    Activations Density 9.663%

    No Known Activations