© 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. 8265
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Firstly" in a document, where a series of points or arguments are being made

    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
    5
    +0.04
    0.5%
    627
    +0.03
    0.5%
    639
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.04
    0.01
    311
    +0.03
    0.01
    366
    +0.03
    0.01
    Negative Logits
     Solitaire
    -0.24
    natureconservancy
    -0.24
    wcs
    -0.23
     depends
    -0.23
     motto
    -0.23
    helps
    -0.23
    axter
    -0.22
     lucky
    -0.22
    assetsadobe
    -0.22
     fragmentation
    -0.22
    POSITIVE LOGITS
    ATER
    0.25
    GROUND
    0.24
     BAT
    0.24
    poke
    0.24
    andowski
    0.24
    20439
    0.23
    ample
    0.23
    BUT
    0.23
    س
    0.22
    UTH
    0.22
    Activations Density 0.002%

    No Known Activations