© 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. 10311
    Prev
    Next
    INDEX
    Explanations

    instances where individuals interact and maintain relationships with others, specifically focusing on friendships and support between individuals

    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
    679
    +0.13
    0.6%
    288
    +0.12
    0.5%
    684
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.19
    679
    +0.12
    0.16
    318
    +0.11
    0.10
    Negative Logits
    Clear
    -0.73
    phabet
    -0.73
    mble
    -0.70
    onew
    -0.68
     disapp
    -0.68
    ptoms
    -0.67
    err
    -0.67
    imar
    -0.66
    ammers
    -0.65
    progress
    -0.64
    POSITIVE LOGITS
    hips
    1.00
    hip
    0.83
     collaborators
    0.79
     partner
    0.78
     Partner
    0.78
     advising
    0.75
     affiliated
    0.75
     collaborating
    0.75
     sponsoring
    0.74
     Supported
    0.73
    Activations Density 4.195%

    No Known Activations