© 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. 12828
    Prev
    Next
    INDEX
    Explanations

    references to firsts and notable achievements

    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
    306
    +0.13
    0.7%
    411
    +0.12
    0.7%
    442
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.13
    0.05
    128
    +0.12
    0.04
    442
    +0.12
    0.05
    Negative Logits
    utes
    -1.98
    áĢº
    -1.87
    ableness
    -1.65
    ---|---|---
    -1.58
    ---|---
    -1.58
    matic
    -1.55
    lements
    -1.54
    neath
    -1.53
    autres
    -1.51
    iginally
    -1.50
    POSITIVE LOGITS
     ever
    2.38
     birthday
    2.25
     girlfriend
    2.17
     stint
    1.97
     wife
    1.92
     encounter
    1.92
     posting
    1.87
    born
    1.84
     cousin
    1.82
     adventures
    1.81
    Activations Density 0.293%

    No Known Activations