© 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. 37205
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and technical documentation

    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
    578
    +0.14
    0.6%
    447
    +0.14
    0.5%
    326
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.14
    0.39
    447
    +0.14
    0.40
    64
    +0.13
    -0.15
    Negative Logits
    tub
    -0.97
    TPS
    -0.84
     SOS
    -0.82
     Saras
    -0.80
    URA
    -0.78
    EMP
    -0.77
     Jackets
    -0.77
     Virtue
    -0.76
     Norn
    -0.74
    Redd
    -0.73
    POSITIVE LOGITS
    aldo
    1.27
    auts
    1.25
     Collider
    1.19
    stadt
    1.15
    igans
    1.07
    omical
    1.04
    ising
    1.02
    tera
    1.01
    autical
    1.00
    omics
    0.98
    Activations Density 7.227%

    No Known Activations