© 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. 3842
    Prev
    Next
    INDEX
    Explanations

    phrases related to restaurants and dining out

    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
    459
    +0.15
    0.6%
    447
    +0.14
    0.6%
    247
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.15
    0.07
    596
    +0.14
    0.09
    211
    +0.12
    -0.06
    Negative Logits
    rogram
    -0.89
     scientists
    -0.85
     declass
    -0.84
    Filename
    -0.83
     physicists
    -0.79
     coron
    -0.78
    heed
    -0.78
     Scientists
    -0.77
     fuzz
    -0.77
    ircraft
    -0.77
    POSITIVE LOGITS
     kios
    1.29
     Cafe
    1.26
     caf
    1.24
     Café
    1.22
     restaurants
    1.21
     cafes
    1.21
     Restaur
    1.20
     Restaurant
    1.19
     restaurant
    1.15
     cafe
    1.14
    Activations Density 22.620%

    No Known Activations