© 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. 26468
    Prev
    Next
    INDEX
    Explanations

    descriptors for properties and qualities of items or situations

    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
    437
    +0.13
    0.7%
    261
    +0.13
    0.7%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.13
    0.11
    293
    +0.13
    0.08
    32
    +0.12
    0.05
    Negative Logits
    ĥ½
    -3.62
    IJ
    -3.35
    ¢
    -3.15
    »
    -3.12
    -3.09
    ↵
    -3.09
    ↵  âĢĥ
    -3.09
    ↵
    -3.09
              ↵
    -3.09
    ↵
    -3.09
    POSITIVE LOGITS
     brackets
    1.69
     ranging
    1.58
     ranges
    1.55
     reflected
    1.52
     labels
    1.49
     backgrounds
    1.47
    asio
    1.45
    âĢIJ
    1.43
    ivat
    1.36
     brands
    1.35
    Activations Density 1.909%

    No Known Activations