© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    expressions related to programming functions and commands

    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
    320
    +0.15
    0.9%
    293
    +0.13
    0.7%
    204
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.15
    0.11
    60
    +0.13
    0.03
    417
    +0.13
    0.09
    Negative Logits
    inea
    -1.62
    hin
    -1.54
    arently
    -1.43
     recurrence
    -1.42
    got
    -1.41
    ipeg
    -1.41
    withstanding
    -1.38
    done
    -1.36
    atinib
    -1.34
    Nil
    -1.34
    POSITIVE LOGITS
    Ļ
    2.29
    ĸ
    2.25
    Ļª
    1.81
    Ń
    1.79
    ¯
    1.75
    ¼
    1.75
    ¢
    1.75
    °
    1.75
    ı
    1.74
    Ĵ
    1.68
    Activations Density 3.975%

    No Known Activations