© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    personal pronouns like 'we', 'us', 'they', and 'them'

    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
    167
    +0.17
    0.7%
    566
    +0.16
    0.7%
    393
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.17
    0.13
    354
    +0.16
    0.12
    551
    +0.16
    0.12
    Negative Logits
    REDACTED
    -0.82
    atory
    -0.70
     gratification
    -0.69
    lights
    -0.69
    math
    -0.68
    more
    -0.66
     Publication
    -0.64
    odor
    -0.63
    fleet
    -0.63
     Mehran
    -0.62
    POSITIVE LOGITS
    've
    1.55
    're
    1.50
    'll
    1.33
    athered
    1.28
    'd
    1.19
    IRD
    1.18
    asel
    1.08
     ourselves
    1.05
    selves
    1.04
    ird
    1.04
    Activations Density 2.278%

    No Known Activations