© 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. 46061
    Prev
    Next
    INDEX
    Explanations

    instances of the word "being."

    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
    +0.17
    0.8%
    566
    +0.16
    0.7%
    393
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.30
    55
    +0.16
    0.20
    566
    +0.15
    0.16
    Negative Logits
     Relief
    -0.72
     Mobility
    -0.71
     srfAttach
    -0.67
    PsyNetMessage
    -0.66
     Lag
    -0.63
     Taxes
    -0.63
     Elements
    -0.63
     Wid
    -0.62
     upbringing
    -0.61
     childbirth
    -0.59
    POSITIVE LOGITS
     able
    1.00
     replaced
    0.98
     evaluated
    0.96
     treated
    0.94
     judged
    0.92
     eaten
    0.89
    amed
    0.88
     exploited
    0.87
     tested
    0.87
     assessed
    0.87
    Activations Density 14.525%

    No Known Activations