© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11019
    Prev
    Next
    INDEX
    Explanations

    years associated with important studies or publications

    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
    396
    +0.12
    0.6%
    71
    +0.11
    0.6%
    341
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.12
    0.03
    341
    +0.11
    0.04
    336
    +0.10
    0.03
    Negative Logits
    ancies
    -1.65
     ways
    -1.60
    arming
    -1.57
     stores
    -1.55
     chance
    -1.55
     today
    -1.55
    encies
    -1.53
     tonight
    -1.53
     yesterday
    -1.49
     waters
    -1.48
    POSITIVE LOGITS
    ¿½
    2.65
    ±
    2.54
    Ļª
    2.25
    ĸ´
    2.20
    ¸
    2.18
    Ĭ
    2.17
    ĨĴ
    2.15
    µ
    2.12
    ¡
    2.08
    Ń
    2.08
    Activations Density 0.096%

    No Known Activations