© 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. 13694
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to methods and procedures

    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
    +0.15
    0.8%
    141
    +0.11
    0.6%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    387
    +0.15
    0.08
    395
    +0.11
    0.08
    238
    +0.11
    0.06
    Negative Logits
    theorem
    -1.60
    toString
    -1.58
    ifier
    -1.53
    evolution
    -1.53
     Clause
    -1.51
     fighter
    -1.50
    ToString
    -1.50
     issue
    -1.50
     theorem
    -1.48
     threat
    -1.48
    POSITIVE LOGITS
    ĻĤ
    2.51
     samples
    2.28
     Samples
    1.94
     specimens
    1.83
     pooled
    1.83
     sample
    1.80
     randomly
    1.77
     collected
    1.74
     respective
    1.68
     triplicate
    1.67
    Activations Density 1.334%

    No Known Activations