© 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. 28514
    Prev
    Next
    INDEX
    Explanations

    initialization functions in code snippets

    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
    376
    +0.15
    0.8%
    95
    +0.14
    0.8%
    130
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.03
    95
    +0.14
    0.03
    324
    +0.13
    0.02
    Negative Logits
    gio
    -1.79
    acic
    -1.77
    oxford
    -1.76
    vereign
    -1.76
    pecific
    -1.68
    off
    -1.57
    Plaintiff
    -1.56
    ming
    -1.53
    cro
    -1.49
    chos
    -1.48
    POSITIVE LOGITS
    ialize
    2.01
    iates
    1.80
    uled
    1.68
    iative
    1.60
     religions
    1.57
     ignition
    1.57
     thinkers
    1.51
    iated
    1.50
     rockets
    1.49
     heroes
    1.49
    Activations Density 0.116%

    No Known Activations