© 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. 2917
    Prev
    Next
    INDEX
    Explanations

    words related to software code and technical structures

    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
    +0.23
    0.8%
    375
    +0.17
    0.6%
    575
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.10
    575
    +0.17
    0.08
    724
    +0.15
    0.07
    Negative Logits
    yah
    -1.16
     Garland
    -1.15
    rising
    -1.13
    cli
    -0.99
    gar
    -0.96
    aire
    -0.95
     grandson
    -0.95
    jin
    -0.92
    cart
    -0.92
    va
    -0.90
    POSITIVE LOGITS
    urally
    1.30
    ural
    1.16
     structure
    1.13
     fractures
    1.09
     formation
    1.08
    ivist
    1.06
     structures
    1.04
    xual
    1.01
     structured
    0.99
    aldehyde
    0.98
    Activations Density 1.119%

    No Known Activations