© 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. 24817
    Prev
    Next
    INDEX
    Explanations

    references to internet-based technologies and services

    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
    57
    +0.13
    0.7%
    478
    +0.11
    0.6%
    292
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.08
    429
    +0.11
    0.05
    150
    +0.10
    0.07
    Negative Logits
    Decided
    -1.56
     insign
    -1.49
    ł
    -1.49
    ariat
    -1.47
     proportions
    -1.46
    §
    -1.44
    naire
    -1.42
    ĥ
    -1.39
     Panthers
    -1.38
    rez
    -1.37
    POSITIVE LOGITS
     Internet
    1.72
    NET
    1.71
    8080
    1.62
     connection
    1.61
     internet
    1.61
    edia
    1.59
     connections
    1.54
    odia
    1.52
    webs
    1.48
    obbsee
    1.47
    Activations Density 1.594%

    No Known Activations