© 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. 8812
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns followed by verbs indicating possession or attribution

    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
    +0.21
    0.8%
    566
    +0.16
    0.6%
    762
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.21
    0.13
    566
    +0.16
    0.13
    762
    +0.13
    0.13
    Negative Logits
     Ammunition
    -0.87
     Globe
    -0.83
     Nanto
    -0.81
    eworthy
    -0.79
     Akron
    -0.78
     Hague
    -0.75
     Yugoslavia
    -0.74
     Kush
    -0.72
    aceutical
    -0.71
     Yel
    -0.71
    POSITIVE LOGITS
    'd
    1.32
    've
    1.22
    'll
    1.21
    're
    1.15
    arers
    0.98
     could
    0.98
     wouldn
    0.95
    innie
    0.94
     shouldn
    0.93
     couldn
    0.93
    Activations Density 1.986%

    No Known Activations