© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35762
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment and dedication

    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
    +0.30
    1.4%
    365
    +0.11
    0.5%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.32
    640
    +0.11
    0.29
    745
    +0.11
    -0.17
    Negative Logits
    DragonMagazine
    -0.96
    soDeliveryDate
    -0.66
    proxy
    -0.65
    isons
    -0.65
    waves
    -0.64
    zynski
    -0.63
    æĺ
    -0.62
    ðŁĺ
    -0.62
    CHR
    -0.61
    ifiers
    -0.60
    POSITIVE LOGITS
     preserving
    0.89
     excellence
    0.86
     improving
    0.86
     maintaining
    0.84
     conserve
    0.83
     secrecy
    0.80
     ensuring
    0.76
     achieving
    0.74
     keeping
    0.74
     uphold
    0.72
    Activations Density 14.804%

    No Known Activations