© 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. 28849
    Prev
    Next
    INDEX
    Explanations

    programming constructs and concepts related to object references and memory management

    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
    156
    +0.34
    2.0%
    376
    +0.14
    0.8%
    161
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.34
    0.04
    299
    +0.14
    0.09
    376
    +0.13
    0.03
    Negative Logits
    Decided
    -1.79
    alian
    -1.56
    ARRANT
    -1.54
    srep
    -1.50
     yet
    -1.46
    ingen
    -1.45
    lain
    -1.39
    еж
    -1.35
     therefore
    -1.35
    TRODUCTION
    -1.32
    POSITIVE LOGITS
    Īĺ
    3.35
    µ
    3.14
    Ĺ
    3.08
    ¿½
    2.95
    ®
    2.80
    ª
    2.78
    ¾
    2.77
    £
    2.74
    ¿
    2.65
    Ł
    2.64
    Activations Density 1.472%

    No Known Activations