© 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. 1-RES-SM
    11. 27230
    Prev
    Next
    INDEX
    Explanations

    terms related to kinetic energy

    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
    156
    +0.15
    0.9%
    223
    +0.12
    0.7%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.18
    156
    +0.12
    0.09
    271
    +0.12
    0.08
    Negative Logits
     hers
    -1.76
    oyal
    -1.65
     happier
    -1.64
    fection
    -1.63
    atus
    -1.55
     behalf
    -1.55
     Debtors
    -1.50
     particular
    -1.48
     mine
    -1.45
    ffic
    -1.42
    POSITIVE LOGITS
    idades
    1.77
    itat
    1.72
    ball
    1.60
    amente
    1.58
    idad
    1.57
    eless
    1.56
    riz
    1.56
    ahead
    1.55
    ologically
    1.52
    ement
    1.51
    Activations Density 0.285%

    No Known Activations