© 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. 2-RES-SM
    11. 10596
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical values or key figures in the context of data or statistics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    277
    +0.16
    0.9%
    369
    +0.16
    0.9%
    261
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.16
    0.06
    67
    +0.16
    0.04
    453
    +0.15
    0.05
    Negative Logits
    reements
    -1.75
     counterpart
    -1.53
    ctions
    -1.48
    ifice
    -1.38
    ellar
    -1.37
    '):
    -1.36
    ipes
    -1.36
     meanwhile
    -1.35
     adjacent
    -1.35
    athi
    -1.34
    POSITIVE LOGITS
    ŀ
    2.73
    ķ
    2.55
    Ĥ
    2.49
    ¿½
    2.38
    ©
    2.36
    ¦
    2.33
    ĥ½
    2.30
    ĸ´
    2.26
    ı
    2.26
    ±
    2.25
    Activations Density 0.222%

    No Known Activations