© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24059
    Prev
    Next
    INDEX
    Explanations

    references to emotional states and personal experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.18
    1.0%
    185
    +0.14
    0.8%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.18
    0.15
    185
    +0.14
    0.13
    11
    +0.13
    0.12
    Negative Logits
    ubernetes
    -1.77
    Ļª
    -1.74
    ument
    -1.67
     representation
    -1.58
    Ŀ
    -1.54
    izumab
    -1.54
    ño
    -1.52
    emente
    -1.50
    inho
    -1.44
    issance
    -1.42
    POSITIVE LOGITS
    alian
    2.07
    chy
    2.00
     rains
    1.86
    ching
    1.71
    yler
    1.65
     hurt
    1.64
     happened
    1.60
    aliana
    1.57
     happen
    1.54
    ÂĴ
    1.51
    Activations Density 0.610%

    No Known Activations