© 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 EvalsExportsAPI 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. 26255
    Prev
    Next
    INDEX
    Explanations

    terms related to data compression

    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
    +0.22
    1.3%
    354
    +0.12
    0.7%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.22
    0.03
    452
    +0.12
    0.03
    111
    +0.12
    0.03
    Negative Logits
    woke
    -1.74
    friends
    -1.72
    ours
    -1.67
    ---|---
    -1.62
     slightest
    -1.60
    nae
    -1.59
     visiting
    -1.57
     friends
    -1.50
    dered
    -1.45
     friend
    -1.45
    POSITIVE LOGITS
    osure
    1.64
    iston
    1.62
    ure
    1.57
     ratio
    1.53
    idone
    1.53
     molding
    1.50
    iere
    1.50
    avier
    1.48
    amycin
    1.47
     rate
    1.47
    Activations Density 0.173%

    No Known Activations