© 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. 28493
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components, particularly in forms or dashboards

    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
    +0.27
    1.6%
    404
    +0.11
    0.7%
    114
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.27
    0.08
    156
    +0.11
    0.05
    271
    +0.10
    0.02
    Negative Logits
     MERCHANTABILITY
    -1.52
    obacteria
    -1.50
     neutrinos
    -1.47
    cules
    -1.47
    ____________
    -1.45
    rely
    -1.42
     virulence
    -1.41
    TRODUCTION
    -1.41
     reason
    -1.39
     polynom
    -1.39
    POSITIVE LOGITS
    lists
    2.03
    sets
    1.95
    list
    1.87
    caster
    1.85
    set
    1.85
     list
    1.77
     lists
    1.75
    gap
    1.71
    chart
    1.66
    screen
    1.60
    Activations Density 0.189%

    No Known Activations