© 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 EvalsExportsAPI 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. 6682
    Prev
    Next
    INDEX
    Explanations

    names of royal figures and references to medieval settings

    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
    +0.18
    0.7%
    721
    +0.13
    0.5%
    447
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.25
    326
    +0.13
    0.19
    99
    +0.13
    0.11
    Negative Logits
    quickShipAvailable
    -1.00
    avez
    -0.96
    enegger
    -0.95
     ADA
    -0.91
     DOE
    -0.89
    ierrez
    -0.89
     GOODMAN
    -0.88
    lando
    -0.88
    ertodd
    -0.88
    ļéĨĴ
    -0.87
    POSITIVE LOGITS
    esses
    1.15
     princes
    1.15
     prince
    1.15
     king
    1.07
     Dwarf
    1.05
     lords
    1.03
     guild
    1.03
    ess
    1.03
     swords
    1.01
    cloth
    1.01
    Activations Density 5.609%

    No Known Activations