© 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. 24134
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mar."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    222
    +0.15
    0.8%
    369
    +0.13
    0.8%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.15
    0.01
    283
    +0.13
    0.02
    222
    +0.12
    0.02
    Negative Logits
     trillion
    -1.45
    JUST
    -1.44
    ferential
    -1.41
    PLC
    -1.39
    MTP
    -1.38
    aeda
    -1.37
     Democratic
    -1.35
     scholarship
    -1.34
     presidents
    -1.33
     emergency
    -1.31
    POSITIVE LOGITS
    iously
    1.85
    oon
    1.81
     onwards
    1.80
    vell
    1.79
    imoto
    1.76
    lin
    1.75
    amycin
    1.64
    onson
    1.62
    quette
    1.60
    inery
    1.58
    Activations Density 0.091%

    No Known Activations