© 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. 2339
    Prev
    Next
    INDEX
    Explanations

    words related to **complicated technical instructions and specifications**

    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
    263
    +0.17
    0.6%
    159
    +0.14
    0.5%
    316
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.17
    0.04
    159
    +0.14
    0.04
    57
    +0.12
    0.04
    Negative Logits
     Sparrow
    -0.91
     Cove
    -0.88
     CPC
    -0.87
     Solitaire
    -0.87
     Wonderland
    -0.87
     Reconstruction
    -0.87
    DonaldTrump
    -0.86
     compe
    -0.86
     Opportun
    -0.85
     Wicked
    -0.84
    POSITIVE LOGITS
    pperc
    1.72
    reth
    1.38
    mpire
    1.25
    prising
    1.24
    seless
    1.19
    bers
    1.19
    pping
    1.18
    ppers
    1.17
    mp
    1.17
    pport
    1.16
    Activations Density 0.494%

    No Known Activations