© 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. 24109
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'S' in various contexts

    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
    369
    +0.21
    1.2%
    362
    +0.19
    1.0%
    371
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.06
    369
    +0.19
    0.04
    371
    +0.12
    0.04
    Negative Logits
    acity
    -1.71
    tails
    -1.50
    avir
    -1.47
    etics
    -1.40
     excess
    -1.38
     meu
    -1.38
    formance
    -1.36
     ')
    -1.36
    orect
    -1.32
     pain
    -1.32
    POSITIVE LOGITS
    CRIPT
    2.06
    PECT
    1.89
    ![
    1.88
    undry
    1.79
    ubl
    1.75
    IGNED
    1.71
    ABA
    1.70
    BN
    1.64
    CRE
    1.62
    IFT
    1.60
    Activations Density 0.172%

    No Known Activations