© 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. 2521
    Prev
    Next
    INDEX
    Explanations

    content related to news articles, tweets, and public figures

    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
    +0.28
    0.9%
    640
    +0.14
    0.5%
    297
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.28
    0.06
    185
    +0.14
    0.06
    297
    +0.13
    0.05
    Negative Logits
    natureconservancy
    -0.95
    forward
    -0.94
    etheless
    -0.93
    withstanding
    -0.90
    finder
    -0.87
    cases
    -0.85
     predec
    -0.84
    vind
    -0.83
     conqu
    -0.81
    worldly
    -0.81
    POSITIVE LOGITS
    000
    1.19
     2008
    1.05
     2017
    1.05
     2007
    1.03
     2009
    1.00
     2010
    1.00
     2016
    0.98
     2006
    0.98
     2015
    0.97
     2014
    0.97
    Activations Density 0.761%

    No Known Activations