© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28246
    Prev
    Next
    INDEX
    Explanations

    terms related to arteries and vascular conditions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    343
    +0.15
    0.8%
    156
    +0.14
    0.8%
    443
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.02
    18
    +0.14
    0.01
    304
    +0.11
    0.01
    Negative Logits
    idays
    -1.78
    ="@+
    -1.70
    >(
    -1.69
    unreadable
    -1.63
     trimester
    -1.61
    selling
    -1.60
     certain
    -1.55
    eting
    -1.53
    ilit
    -1.52
     national
    -1.49
    POSITIVE LOGITS
    imuth
    1.82
    ¢
    1.76
    anches
    1.75
     lumen
    1.70
    ient
    1.68
    ients
    1.66
    ħ
    1.62
     endothelium
    1.61
     endothelial
    1.60
    wood
    1.58
    Activations Density 0.040%

    No Known Activations