© 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. 10950
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring quality and reliability

    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
    +0.24
    1.4%
    466
    +0.20
    1.2%
    348
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.24
    0.06
    307
    +0.20
    0.08
    490
    +0.18
    0.04
    Negative Logits
     question
    -1.66
    cias
    -1.59
     disappoint
    -1.53
    ulator
    -1.43
    atinib
    -1.36
    terday
    -1.36
     Question
    -1.34
    ertation
    -1.34
    opter
    -1.33
    mand
    -1.33
    POSITIVE LOGITS
    č↵
    2.12
    ↵
    2.12
    <|outofrange|>
    2.12
    ↵
    2.12
    ↵
    2.12
    2.12
    ↵↵
    2.12
    <|outofrange|>
    2.12
    ↵
    2.12
    2.12
    Activations Density 0.685%

    No Known Activations