© 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 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. 30457
    Prev
    Next
    INDEX
    Explanations

    references to various types of simulations and modeling

    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
    +0.18
    1.0%
    182
    +0.14
    0.8%
    160
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.18
    0.03
    177
    +0.14
    0.02
    365
    +0.13
    0.02
    Negative Logits
    §
    -2.15
    ī
    -2.04
    ½
    -1.99
    ¯
    -1.94
    į
    -1.92
    Ħ
    -1.82
    º
    -1.81
    ¬
    -1.75
    Į
    -1.75
    ·
    -1.74
    POSITIVE LOGITS
    nament
    2.09
     experiments
    1.81
     simulations
    1.76
     annealing
    1.75
     tomography
    1.65
     settings
    1.58
    ample
    1.57
     sket
    1.57
    ulation
    1.55
     simulation
    1.54
    Activations Density 0.218%

    No Known Activations