© 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. 2-RES-SM
    11. 31882
    Prev
    Next
    INDEX
    Explanations

    specific historical dates related to significant events

    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
    422
    +0.16
    0.9%
    161
    +0.15
    0.8%
    342
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.16
    0.04
    342
    +0.15
    0.04
    485
    +0.12
    0.03
    Negative Logits
    áĢ¯
    -2.06
    àµį
    -1.82
    лÑı
    -1.75
    à±
    -1.75
    à°¿
    -1.72
    áĢ¬
    -1.71
    à±ģ
    -1.67
    cknowled
    -1.65
     NOTICE
    -1.60
    ÑĢаз
    -1.60
    POSITIVE LOGITS
     onwards
    2.11
     onward
    1.98
     weddings
    1.57
    olt
    1.47
     salaries
    1.47
     opponents
    1.43
     Hospit
    1.42
     occasions
    1.40
     departments
    1.37
     hospitals
    1.37
    Activations Density 0.661%

    No Known Activations