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

    Neuronpedia

    Jacobian LensNEW
    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. 26058
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their derivatives related to biological processes

    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
    111
    +0.14
    0.8%
    237
    +0.12
    0.7%
    441
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.14
    0.16
    428
    +0.12
    0.12
    256
    +0.11
    0.13
    Negative Logits
    lessly
    -1.61
     delay
    -1.53
    ually
    -1.51
     day
    -1.46
     favor
    -1.42
     slightest
    -1.33
     caret
    -1.32
     mornings
    -1.31
     foregoing
    -1.31
    ORM
    -1.28
    POSITIVE LOGITS
    isms
    1.84
    glycer
    1.71
    ème
    1.68
    ¢
    1.67
    Ĵ
    1.63
    ¿
    1.61
    fecture
    1.60
    /-
    1.59
    ģ
    1.55
    ĥ
    1.54
    Activations Density 0.874%

    No Known Activations