© 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. 29630
    Prev
    Next
    INDEX
    Explanations

    words that convey strong positive emotions or highlight exceptional qualities

    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
    118
    +0.14
    0.8%
    56
    +0.11
    0.6%
    148
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.14
    0.07
    148
    +0.11
    0.02
    119
    +0.10
    0.03
    Negative Logits
    agra
    -1.65
    ainer
    -1.64
    ves
    -1.57
    ters
    -1.57
    heses
    -1.56
    tico
    -1.55
    tern
    -1.53
    Åij
    -1.53
    uelle
    -1.53
    ár
    -1.53
    POSITIVE LOGITS
    µ
    1.90
    ¨
    1.82
    ľĵ
    1.78
    ®
    1.73
     amounts
    1.72
    Ī
    1.72
    Ł
    1.70
    č↵
    1.68
       ↵
    1.68
    ↵
    1.68
    Activations Density 0.481%

    No Known Activations