© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27172
    Prev
    Next
    INDEX
    Explanations

    mentions of amino acids and nucleic acids

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    203
    +0.12
    0.7%
    2
    +0.11
    0.6%
    372
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.01
    111
    +0.11
    0.01
    271
    +0.11
    0.00
    Negative Logits
    rely
    -1.90
    olor
    -1.80
     same
    -1.76
    night
    -1.73
    ockey
    -1.61
    urchase
    -1.60
     Spacewatch
    -1.59
     why
    -1.58
    quire
    -1.54
    return
    -1.53
    POSITIVE LOGITS
    ¤
    2.90
    ¬
    2.25
    İ
    2.19
    ī
    2.05
    ħ
    2.00
    Ģ
    1.99
    Ĵ
    1.98
    ¨
    1.96
    ¢
    1.93
    ¾
    1.92
    Activations Density 0.077%

    No Known Activations