© 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. 13861
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and cooking

    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
    285
    +0.11
    0.5%
    723
    +0.11
    0.5%
    715
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.11
    0.08
    476
    +0.11
    0.03
    642
    +0.10
    0.02
    Negative Logits
    DragonMagazine
    -0.88
    manship
    -0.86
     GOODMAN
    -0.82
    STER
    -0.74
     Hunters
    -0.73
     Respond
    -0.69
     Heist
    -0.66
    iary
    -0.64
    CLASS
    -0.63
     reconc
    -0.62
    POSITIVE LOGITS
    ighton
    1.07
    aking
    1.02
    aky
    1.01
    eping
    0.95
    ase
    0.91
    vice
    0.89
    atio
    0.89
    mination
    0.88
    ndra
    0.87
    ruption
    0.87
    Activations Density 6.602%

    No Known Activations