© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2741
    Prev
    Next
    INDEX
    Explanations

    instances of the word "settle" or variations of it, such as "settling" or "settled," usually related to making a decision or coming to a resolution

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.16
    0.6%
    283
    +0.15
    0.6%
    566
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.16
    0.05
    70
    +0.15
    0.04
    113
    +0.13
    0.03
    Negative Logits
    emic
    -0.96
    eway
    -0.95
    erve
    -0.94
    icipated
    -0.90
     manifested
    -0.84
    saf
    -0.83
    ocalypse
    -0.83
    omics
    -0.83
    emonic
    -0.81
     Canaveral
    -0.81
    POSITIVE LOGITS
     settling
    1.11
     settle
    1.09
    ters
    1.04
     footing
    0.99
    sett
    0.91
    tered
    0.91
     upon
    0.89
     settles
    0.88
    itating
    0.87
    tons
    0.86
    Activations Density 0.516%

    No Known Activations