© 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. 7443
    Prev
    Next
    INDEX
    Explanations

    examples of direct speech

    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
    393
    +0.19
    0.7%
    326
    +0.16
    0.6%
    564
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    519
    +0.19
    0.09
    767
    +0.16
    0.08
    8
    +0.13
    0.08
    Negative Logits
     Prior
    -0.82
     Spani
    -0.81
     Britons
    -0.75
    Brit
    -0.74
     Rothschild
    -0.73
     Pharaoh
    -0.73
     Rebell
    -0.73
     Gaul
    -0.72
     snipp
    -0.70
     Levant
    -0.69
    POSITIVE LOGITS
    pecially
    0.98
    forth
    0.97
    lightly
    0.96
     gonna
    0.95
    orno
    0.95
    edition
    0.91
    aurus
    0.91
    ashtra
    0.88
    ensibly
    0.85
    ustainable
    0.84
    Activations Density 0.930%

    No Known Activations