© 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. 39827
    Prev
    Next
    INDEX
    Explanations

    content related to economic growth and financial matters, including data, projections, and analysis

    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
    +0.13
    0.8%
    248
    +0.13
    0.8%
    391
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.13
    0.07
    248
    +0.13
    0.07
    690
    +0.07
    0.09
    Negative Logits
    edi
    -0.56
    ENE
    -0.52
    acterial
    -0.48
    street
    -0.48
    nen
    -0.48
     Jedi
    -0.47
     folders
    -0.47
     Zan
    -0.47
    YC
    -0.46
     Planes
    -0.45
    POSITIVE LOGITS
     Unemployment
    0.62
     recession
    0.58
    ageddon
    0.56
    essim
    0.53
    Ĥİ
    0.53
    stim
    0.53
     slowdown
    0.52
     stabilization
    0.51
    abil
    0.51
     Recession
    0.51
    Activations Density 16.099%

    No Known Activations