© 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. 23776
    Prev
    Next
    INDEX
    Explanations

    proper names

    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
    156
    +0.15
    0.8%
    258
    +0.14
    0.8%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.07
    385
    +0.14
    0.06
    43
    +0.14
    0.06
    Negative Logits
    board
    -1.83
    ritic
    -1.64
    .""
    -1.56
     transgender
    -1.56
    unes
    -1.55
    irm
    -1.54
    chter
    -1.53
    ensors
    -1.53
    uture
    -1.51
    inct
    -1.51
    POSITIVE LOGITS
    issance
    1.81
     Neumann
    1.61
     Hoover
    1.60
     Stadium
    1.60
    cks
    1.57
     Boulevard
    1.57
     Wright
    1.56
    SON
    1.49
    ftware
    1.45
     wrote
    1.44
    Activations Density 0.211%

    No Known Activations