© 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. 2-RES-SM
    6. 11036
    Prev
    Next
    INDEX
    Explanations

    terms related to inflammation and its effects on cells

    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
    156
    +0.23
    1.4%
    186
    +0.13
    0.8%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.23
    0.01
    349
    +0.13
    0.01
    359
    +0.12
    0.01
    Negative Logits
    \!\
    -1.73
     interested
    -1.64
    jour
    -1.62
    gmail
    -1.62
    arrant
    -1.59
    yahoo
    -1.55
     vez
    -1.54
    pinion
    -1.54
    aucoup
    -1.54
     yours
    -1.53
    POSITIVE LOGITS
    £
    3.37
    Ĩ
    3.15
    ¢
    3.14
    ł
    3.08
    Ħ
    3.05
    ¶
    2.84
    µ
    2.77
    Ł
    2.77
    ĩ
    2.76
    ¡
    2.75
    Activations Density 0.057%

    No Known Activations