© 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. 31334
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer applications and development, such as "application", "API", "module", "implementation", "demonstration", and "software"

    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
    +0.27
    1.1%
    496
    +0.14
    0.6%
    623
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.27
    0.04
    575
    +0.14
    0.10
    444
    +0.14
    0.04
    Negative Logits
    ãĥĥãĥī
    -0.86
    rolet
    -0.82
    ²¾
    -0.78
    apes
    -0.77
    ord
    -0.75
    aults
    -0.72
    etsk
    -0.69
    ault
    -0.69
    UCT
    -0.68
    king
    -0.68
    POSITIVE LOGITS
    earance
    0.87
    mable
    0.87
    rehens
    0.86
     launcher
    0.82
    matically
    0.81
     applications
    0.79
     appl
    0.78
    eering
    0.76
     application
    0.75
    Crash
    0.75
    Activations Density 5.951%

    No Known Activations