© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4654
    Prev
    Next
    INDEX
    Explanations

    information about cultural practices and customs related to various countries and regions

    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
    659
    +0.20
    0.7%
    578
    +0.20
    0.7%
    67
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.20
    0.12
    208
    +0.20
    0.12
    564
    +0.16
    0.10
    Negative Logits
    ĪĴ
    -1.19
     Grateful
    -0.93
     Tinder
    -0.92
     Yamaha
    -0.92
    ãĥĹ
    -0.91
    Magikarp
    -0.87
     explan
    -0.84
     contagious
    -0.82
     Tycoon
    -0.82
     rake
    -0.81
    POSITIVE LOGITS
    ursor
    1.71
    ologne
    1.67
    redits
    1.65
    oding
    1.65
    ortex
    1.63
    ounters
    1.60
    ourses
    1.59
    rawl
    1.59
    rossover
    1.58
    ursed
    1.57
    Activations Density 6.572%

    No Known Activations