© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36967
    Prev
    Next
    INDEX
    Explanations

    lessons or teachings mentioned in a narrative context

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.20
    0.9%
    567
    +0.11
    0.5%
    606
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.34
    255
    +0.11
    0.15
    160
    +0.10
    0.23
    Negative Logits
    lished
    -0.76
    cohol
    -0.73
    omo
    -0.72
    igham
    -0.71
    vertisement
    -0.69
    idia
    -0.67
    riott
    -0.67
    etermined
    -0.66
    ordering
    -0.64
    pload
    -0.64
    POSITIVE LOGITS
     lesson
    1.15
     firsthand
    1.01
     lessons
    0.94
     anew
    0.81
     basics
    0.80
     Lessons
    0.79
     humility
    0.77
     skills
    0.76
     tricks
    0.74
     Parables
    0.71
    Activations Density 17.059%

    No Known Activations