© 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. 28204
    Prev
    Next
    INDEX
    Explanations

    years mentioned in a document

    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
    30
    +0.13
    0.7%
    436
    +0.12
    0.7%
    74
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.13
    0.04
    238
    +0.12
    0.04
    51
    +0.11
    0.03
    Negative Logits
     guilt
    -1.71
     latter
    -1.66
     ownership
    -1.62
     his
    -1.61
     hers
    -1.61
     those
    -1.58
     trace
    -1.54
     question
    -1.54
     above
    -1.51
     branches
    -1.48
    POSITIVE LOGITS
    vier
    1.96
    icolor
    1.94
    nai
    1.82
    elijk
    1.81
    grid
    1.78
    nen
    1.74
    peg
    1.71
    ystem
    1.70
    iewicz
    1.69
    INLINE
    1.65
    Activations Density 0.115%

    No Known Activations