© 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. 28293
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to data formats and programming

    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
    198
    +0.17
    1.0%
    459
    +0.14
    0.8%
    442
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.17
    0.12
    78
    +0.14
    0.06
    452
    +0.14
    0.06
    Negative Logits
    oxford
    -1.68
    inctions
    -1.64
    taient
    -1.62
    anas
    -1.59
     prices
    -1.58
    ants
    -1.54
     interests
    -1.51
    alties
    -1.50
     budgets
    -1.47
    isma
    -1.47
    POSITIVE LOGITS
    ³
    4.25
    Ĥ¬
    4.21
    Ļ
    4.17
    ¬
    4.14
    IJ
    4.12
    §
    4.07
    ĵ
    4.07
    ħ
    4.04
    Ĩ
    4.03
    ŀ
    4.02
    Activations Density 1.920%

    No Known Activations