© 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. 1-RES-SM
    11. 24160
    Prev
    Next
    INDEX
    Explanations

    references to cultural or artistic expressions, particularly in the context of food and beverage

    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
    243
    +0.14
    0.8%
    197
    +0.12
    0.7%
    262
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.14
    0.03
    243
    +0.12
    0.03
    120
    +0.12
    0.02
    Negative Logits
    ħ
    -3.01
    ĵ
    -2.82
    ½
    -2.71
    ŀ
    -2.61
    ¨
    -2.58
    ®
    -2.57
    ľ
    -2.56
    ·¸
    -2.49
    ľĵ
    -2.49
    ¡
    -2.46
    POSITIVE LOGITS
    innings
    2.16
    lez
    1.79
    erville
    1.65
    ilage
    1.64
    ellation
    1.58
    ender
    1.57
    arp
    1.55
    ings
    1.53
    arser
    1.51
    borough
    1.50
    Activations Density 0.264%

    No Known Activations