© 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. 1-RES-SM
    11. 28361
    Prev
    Next
    INDEX
    Explanations

    references to the Internet and its related concepts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    0.9%
    170
    +0.11
    0.6%
    451
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.15
    0.02
    170
    +0.11
    0.02
    35
    +0.11
    0.01
    Negative Logits
     tear
    -1.82
     solitary
    -1.68
     little
    -1.67
     unequal
    -1.65
     drastic
    -1.54
     lethal
    -1.52
     reasonable
    -1.50
    yy
    -1.48
     union
    -1.48
     away
    -1.48
    POSITIVE LOGITS
     Explorer
    1.89
    borne
    1.88
    Link
    1.79
    obi
    1.72
    works
    1.71
    Gate
    1.66
    MW
    1.65
     Archive
    1.59
     Marketing
    1.58
    sphere
    1.57
    Activations Density 0.064%

    No Known Activations