© 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. 9094
    Prev
    Next
    INDEX
    Explanations

    phrases related to space exploration, astronomy, and galaxy

    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
    649
    +0.17
    0.6%
    130
    +0.17
    0.6%
    213
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.17
    0.04
    213
    +0.17
    0.03
    130
    +0.17
    0.03
    Negative Logits
    erer
    -0.96
    CHAT
    -0.96
    è¦ļéĨĴ
    -0.94
     CTR
    -0.94
     Turing
    -0.89
     Hearts
    -0.88
    yrinth
    -0.88
     Warrant
    -0.87
     PowerPoint
    -0.86
    00000
    -0.85
    POSITIVE LOGITS
    mopolitan
    1.76
    metics
    1.49
    cos
    1.49
    metic
    1.41
    mop
    1.30
    mic
    1.24
    met
    1.24
    idon
    1.21
    entric
    1.15
    nova
    1.12
    Activations Density 0.501%

    No Known Activations