© 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. 34014
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to individuals

    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
    447
    +0.35
    1.7%
    393
    +0.17
    0.8%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.35
    0.21
    139
    +0.17
    0.10
    283
    +0.10
    0.03
    Negative Logits
     Anything
    -0.67
    ³³³³
    -0.63
     Bound
    -0.62
     VIDEOS
    -0.61
     Anyway
    -0.61
    BACK
    -0.59
    ãĤª
    -0.59
     Delicious
    -0.57
     Federation
    -0.56
     Beet
    -0.55
    POSITIVE LOGITS
    oping
    1.01
    oped
    0.94
     accompanies
    0.93
     frequ
    0.91
    soever
    0.88
     preceded
    0.88
     resided
    0.84
     specialize
    0.81
     accompanied
    0.81
     specializes
    0.80
    Activations Density 10.181%

    No Known Activations