© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10407
    Prev
    Next
    INDEX
    Explanations

    mentions of film directors and their work, specifically focusing on Christopher Nolan and J.J. Abrams

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    670
    +0.14
    0.5%
    549
    +0.12
    0.5%
    382
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.14
    0.10
    76
    +0.12
    0.09
    670
    +0.12
    0.08
    Negative Logits
     Flask
    -0.89
    attled
    -0.88
    ibaba
    -0.88
    usterity
    -0.87
     WTO
    -0.86
    aram
    -0.86
    ĪĴ
    -0.86
     uninsured
    -0.84
     nurses
    -0.84
    tnc
    -0.84
    POSITIVE LOGITS
     Studios
    1.38
     Publisher
    1.10
     Productions
    1.08
     Animation
    1.07
    Studio
    1.07
     Spielberg
    1.06
     adaptation
    1.05
     Studio
    1.05
     Premiere
    1.03
     studios
    1.03
    Activations Density 3.505%

    No Known Activations