© 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. 2-RES-SM
    11. 31443
    Prev
    Next
    INDEX
    Explanations

    phrases related to pharmaceutical treatments and dosages

    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
    478
    +0.16
    0.9%
    129
    +0.15
    0.8%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.16
    0.08
    362
    +0.15
    0.08
    510
    +0.13
    0.08
    Negative Logits
    guard
    -1.70
    atures
    -1.64
    oire
    -1.62
    guards
    -1.61
     aside
    -1.60
    hesis
    -1.59
    back
    -1.58
    erior
    -1.55
    away
    -1.54
    де
    -1.51
    POSITIVE LOGITS
    ↵
    4.59
    ↵  âĢĥ
    4.59
    č↵
    4.59
    4.59
    4.59
    ↵
    4.59
              ↵
    4.59
    4.59
    ↵
    4.59
    ↵↵
    4.59
    Activations Density 0.378%

    No Known Activations