© 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. 2-RES-SM
    11. 28372
    Prev
    Next
    INDEX
    Explanations

    special characters and sequences related to code formatting or programming

    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
    136
    +0.14
    0.8%
    501
    +0.12
    0.7%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.14
    0.05
    501
    +0.12
    0.03
    493
    +0.12
    0.05
    Negative Logits
    alus
    -1.85
    izumab
    -1.80
    operated
    -1.73
    imir
    -1.57
    inin
    -1.50
    unlock
    -1.50
    uthan
    -1.49
    icillin
    -1.48
    orsche
    -1.48
    icides
    -1.46
    POSITIVE LOGITS
    ½
    2.75
    ¼
    2.50
    »
    2.45
    Ĺ
    2.45
    Ģ
    2.44
    ¡
    2.37
    ĭ
    2.33
    ¨
    2.30
    Ĥ¬
    2.27
    ©
    2.26
    Activations Density 0.302%

    No Known Activations