© 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. 4-RES-SM
    11. 8893
    Prev
    Next
    INDEX
    Explanations

    technical terms and methodologies related to biochemical experiments and assays

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    451
    +0.13
    0.7%
    495
    +0.12
    0.7%
    507
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.13
    0.02
    189
    +0.12
    0.02
    148
    +0.11
    0.01
    Negative Logits
     matter
    -1.59
     puzzle
    -1.48
    abouts
    -1.45
     missing
    -1.44
     forgiven
    -1.39
     welcome
    -1.39
     imagin
    -1.39
     lur
    -1.36
     considerable
    -1.35
     autism
    -1.35
    POSITIVE LOGITS
     chromatography
    1.68
     chromat
    1.58
    Tube
    1.58
    tration
    1.57
     coupled
    1.57
     cartridges
    1.54
     method
    1.53
     methods
    1.50
     fingerprints
    1.50
     techniques
    1.47
    Activations Density 0.063%

    No Known Activations