© 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. 4-RES-SM
    11. 12485
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to cellular processes and mechanisms in biology

    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
    21
    +0.27
    1.6%
    78
    +0.17
    1.0%
    240
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.27
    0.03
    203
    +0.17
    0.02
    148
    +0.14
    0.02
    Negative Logits
     mine
    -1.73
     fact
    -1.51
     Trek
    -1.46
     Monte
    -1.42
     ours
    -1.37
     yours
    -1.37
     premium
    -1.35
     hire
    -1.30
     fit
    -1.30
     Books
    -1.29
    POSITIVE LOGITS
    Ļ
    3.84
    ij
    3.42
    ģ
    3.42
    ³
    3.38
    ŀ
    3.38
    į
    3.37
    Ģ
    3.31
    Ĩ
    3.28
    Ĵ
    3.26
    ħ
    3.25
    Activations Density 0.133%

    No Known Activations