© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12046
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions related to faith and devotion

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    20
    +0.14
    0.8%
    352
    +0.12
    0.7%
    371
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.02
    20
    +0.12
    0.04
    222
    +0.12
    0.02
    Negative Logits
    ·¸
    -1.94
    /~
    -1.93
    ±
    -1.85
    §
    -1.77
    ¡
    -1.75
    µ
    -1.66
    ¿½
    -1.61
    «
    -1.57
    ĻĤ
    -1.54
    ¥
    -1.53
    POSITIVE LOGITS
    rios
    1.63
    Äį
    1.58
     fourth
    1.48
    emi
    1.42
    4
    1.42
    urus
    1.42
    ème
    1.40
    î
    1.38
    sson
    1.33
    ctomy
    1.33
    Activations Density 0.390%

    No Known Activations