© 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. 10666
    Prev
    Next
    INDEX
    Explanations

    a specific numeric pattern present in a series of text strings

    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
    628
    +0.05
    0.6%
    694
    +0.04
    0.5%
    756
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.05
    0.01
    416
    +0.04
    0.01
    633
    +0.04
    0.01
    Negative Logits
     Croat
    -0.28
     hypothesis
    -0.27
    issance
    -0.26
     MOR
    -0.26
     Rising
    -0.26
     Millenn
    -0.25
     Somers
    -0.24
     PowerPoint
    -0.24
     Sawyer
    -0.24
    reality
    -0.23
    POSITIVE LOGITS
    illet
    0.32
    erb
    0.31
    ammy
    0.30
    abal
    0.29
    tx
    0.28
    Ti
    0.28
    inker
    0.28
    abad
    0.27
    acia
    0.27
    het
    0.27
    Activations Density 0.001%

    No Known Activations