© 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 EvalsExportsinterp-engineNEWAPI 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. 27961
    Prev
    Next
    INDEX
    Explanations

    references to data structures and programming constructs in code

    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
    199
    +0.13
    0.7%
    369
    +0.13
    0.7%
    186
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.13
    0.11
    220
    +0.13
    0.07
    199
    +0.13
    0.05
    Negative Logits
    ionale
    -1.56
    rolled
    -1.45
    gery
    -1.41
    QUE
    -1.41
    ique
    -1.40
    lining
    -1.39
    ungen
    -1.37
    clamation
    -1.34
    strings
    -1.34
    phony
    -1.34
    POSITIVE LOGITS
    Ļª
    6.05
    č↵
    5.85
    ↵
    5.85
    ↵Č
    5.85
    ↵↵↵
    5.85
    ↵↵
    5.85
    5.85
    <|outofrange|>
    5.85
       ↵
    5.85
    č↵
    5.85
    Activations Density 3.551%

    No Known Activations