© 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. 30487
    Prev
    Next
    INDEX
    Explanations

    variations of the word "way" in different contexts

    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
    457
    +0.11
    0.6%
    341
    +0.10
    0.6%
    320
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.11
    0.02
    15
    +0.10
    0.03
    249
    +0.10
    0.02
    Negative Logits
     whom
    -1.70
    acy
    -1.69
    rile
    -1.59
    jar
    -1.50
     hemorrhage
    -1.49
     death
    -1.40
    itud
    -1.39
     influenza
    -1.36
    yz
    -1.36
     hol
    -1.33
    POSITIVE LOGITS
    ĸ
    1.86
    ³
    1.85
    ±
    1.80
    ↵
    1.78
    ↵
    1.78
    č↵
    1.78
    ↵
    1.78
    ↵
    1.78
    <|outofrange|>
    1.78
    ↵  ³³³
    1.78
    Activations Density 0.146%

    No Known Activations