© 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. 13194
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rel" indicating relationships or connections

    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
    255
    +0.15
    0.8%
    348
    +0.12
    0.7%
    318
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.02
    213
    +0.12
    0.02
    255
    +0.10
    0.00
    Negative Logits
    lla
    -1.70
     forth
    -1.70
    zione
    -1.63
     ourselves
    -1.52
    hole
    -1.48
    ttes
    -1.45
     Himself
    -1.43
     herself
    -1.40
     mean
    -1.37
     circulation
    -1.36
    POSITIVE LOGITS
    igion
    2.56
    iance
    2.52
    apse
    2.40
    ©
    2.32
    apsing
    2.30
    ief
    2.24
    iant
    2.22
    igious
    2.21
    ¡
    2.20
    ³
    2.12
    Activations Density 0.143%

    No Known Activations