© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28280
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to parenting styles and approaches

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    153
    +0.17
    1.0%
    156
    +0.13
    0.8%
    240
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.17
    0.05
    240
    +0.13
    -0.02
    153
    +0.13
    0.03
    Negative Logits
    ault
    -1.52
     withdraw
    -1.46
    fecture
    -1.44
    started
    -1.39
    fork
    -1.36
    reset
    -1.36
    doibase
    -1.34
    stop
    -1.32
    loader
    -1.32
     stuck
    -1.27
    POSITIVE LOGITS
     sexes
    2.07
     favorably
    1.95
    oretic
    1.79
     respects
    1.66
    orems
    1.57
    inction
    1.56
     favor
    1.52
    asons
    1.50
     perspective
    1.49
     respect
    1.48
    Activations Density 1.947%

    No Known Activations