© 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. 26040
    Prev
    Next
    INDEX
    Explanations

    instances of significant actions or concepts within a narrative or argument

    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
    393
    +0.13
    0.7%
    322
    +0.12
    0.7%
    149
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.13
    0.02
    80
    +0.12
    0.02
    169
    +0.11
    0.01
    Negative Logits
     infra
    -1.96
     sights
    -1.70
     enough
    -1.55
     include
    -1.53
     includes
    -1.46
     hosts
    -1.43
     arteries
    -1.41
     supra
    -1.39
     skies
    -1.38
    Ĥ
    -1.36
    POSITIVE LOGITS
    ···
    1.74
    ishops
    1.67
    ibernate
    1.60
    tow
    1.56
    TTP
    1.53
    sie
    1.52
    quarter
    1.52
    olean
    1.50
    ytes
    1.45
    ublin
    1.43
    Activations Density 0.193%

    No Known Activations