© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3150
    Prev
    Next
    INDEX
    Explanations

    unique syntax elements and programming concepts such as procedure, syntax, method invocation, and naming conventions

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.18
    0.7%
    308
    +0.11
    0.4%
    11
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.14
    575
    +0.11
    0.11
    255
    +0.11
    0.08
    Negative Logits
    icer
    -0.97
    gren
    -0.92
    vation
    -0.89
    ilee
    -0.88
    vic
    -0.88
    akra
    -0.86
    onna
    -0.85
    cia
    -0.85
    tro
    -0.83
    awar
    -0.81
    POSITIVE LOGITS
     layout
    0.96
    eering
    0.96
     diagram
    0.95
     layouts
    0.95
     mismatch
    0.94
    eers
    0.93
     diagrams
    0.88
     format
    0.86
     formats
    0.83
     Pattern
    0.82
    Activations Density 1.672%

    No Known Activations