© 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. 36937
    Prev
    Next
    INDEX
    Explanations

    financial terms and numbers related to various organizations and individuals

    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
    447
    +0.22
    1.0%
    35
    +0.13
    0.6%
    91
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.22
    0.41
    35
    +0.13
    0.07
    34
    +0.11
    0.07
    Negative Logits
     goggles
    -0.80
     astronauts
    -0.77
    Spoiler
    -0.74
    ĪĴ
    -0.74
     clim
    -0.69
    Ĥ¬
    -0.69
     focal
    -0.65
     wavelength
    -0.65
     snipers
    -0.64
     Riding
    -0.63
    POSITIVE LOGITS
     payable
    1.44
     receipts
    1.33
     payments
    1.31
     repayment
    1.31
     debts
    1.29
     creditor
    1.27
     owed
    1.24
     creditors
    1.19
     repay
    1.19
     payment
    1.15
    Activations Density 27.621%

    No Known Activations