© 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 EvalsExportsinterp-engineNEWAPI 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. 13533
    Prev
    Next
    INDEX
    Explanations

    references to the organization and XML schema structure

    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
    466
    +0.21
    1.2%
    78
    +0.15
    0.9%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.21
    0.02
    425
    +0.15
    0.03
    412
    +0.11
    0.03
    Negative Logits
     fasc
    -1.61
    pert
    -1.51
    piece
    -1.48
    cer
    -1.40
    naments
    -1.38
     reminded
    -1.33
     perfectly
    -1.31
     suit
    -1.27
     hyperplasia
    -1.26
     precisely
    -1.25
    POSITIVE LOGITS
    /
    2.25
    ĨĴ
    2.18
    ³
    2.12
    2.08
    <|outofrange|>
    2.08
    ↵
    2.08
    2.08
    2.08
    ↵
    2.08
    <|outofrange|>
    2.08
    Activations Density 0.058%

    No Known Activations