© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    specific types of agricultural and environmental terms, particularly related to crops and pests

    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
    307
    +0.17
    1.0%
    156
    +0.17
    1.0%
    348
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.17
    0.07
    1
    +0.17
    0.04
    440
    +0.16
    0.01
    Negative Logits
    edly
    -1.85
    blockList
    -1.70
    ickets
    -1.57
    ãĤį
    -1.56
    anchester
    -1.46
    zitter
    -1.45
    sible
    -1.41
    MHz
    -1.41
    card
    -1.39
    zza
    -1.38
    POSITIVE LOGITS
    5.02
    5.02
    ↵↵
    5.02
    ↵
    5.02
    5.02
    5.02
    č↵
    5.02
    ↵
    5.02
         ↵
    5.02
    ↵
    5.02
    Activations Density 0.971%

    No Known Activations