© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and change

    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
    +0.18
    0.6%
    679
    +0.16
    0.6%
    575
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.18
    0.06
    271
    +0.16
    0.04
    221
    +0.14
    0.04
    Negative Logits
    NetMessage
    -1.12
    beck
    -1.02
     Straw
    -1.00
    vin
    -0.92
    leton
    -0.92
    lua
    -0.91
    itto
    -0.88
    ãĤ·ãĥ£
    -0.86
    IPP
    -0.86
    ships
    -0.85
    POSITIVE LOGITS
    ments
    1.07
     efficiency
    1.04
     productivity
    1.02
     tremend
    1.01
     materially
    0.99
     markedly
    0.95
     exponentially
    0.94
     outcomes
    0.94
     transparency
    0.92
     responsiveness
    0.92
    Activations Density 1.024%

    No Known Activations