© 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. 28429
    Prev
    Next
    INDEX
    Explanations

    programming jargon and technical terms

    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
    419
    +0.18
    1.0%
    400
    +0.16
    1.0%
    186
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.18
    0.05
    450
    +0.16
    0.09
    7
    +0.15
    0.00
    Negative Logits
    §
    -3.05
    Ļª
    -2.79
    ī
    -2.74
    ĭ
    -2.63
    į
    -2.61
    Ĺ
    -2.59
    Ŀ
    -2.58
    ¡
    -2.57
    ±
    -2.56
    Ń
    -2.50
    POSITIVE LOGITS
     itself
    1.67
     lies
    1.48
    agus
    1.47
     things
    1.42
    ITED
    1.39
     always
    1.36
    ithe
    1.34
     nationalism
    1.31
    ubation
    1.30
    keit
    1.29
    Activations Density 4.348%

    No Known Activations