© 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. 36924
    Prev
    Next
    INDEX
    Explanations

    information related to groundwater management, water contamination, and environmental protection measures such as filtering and irrigation systems

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    739
    +0.13
    0.6%
    178
    +0.12
    0.5%
    644
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.13
    0.16
    564
    +0.12
    0.12
    316
    +0.12
    0.10
    Negative Logits
    emort
    -0.75
    ovie
    -0.74
    >[
    -0.74
    akia
    -0.74
    anu
    -0.71
    uggage
    -0.70
    */(
    -0.70
    otine
    -0.70
    zhen
    -0.70
    stars
    -0.66
    POSITIVE LOGITS
     irrig
    0.97
    gency
    0.91
     dams
    0.90
    holes
    0.87
    banks
    0.84
     irrigation
    0.84
    melon
    0.84
     pipes
    0.84
     watershed
    0.83
     advis
    0.82
    Activations Density 12.730%

    No Known Activations