© 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. 26060
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms that refer to medical or technical standards and procedures

    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
    502
    +0.14
    0.8%
    369
    +0.14
    0.8%
    195
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.14
    0.03
    281
    +0.14
    0.02
    508
    +0.11
    0.02
    Negative Logits
     complete
    -1.95
     recommend
    -1.79
     reply
    -1.78
     stomach
    -1.70
     completion
    -1.67
    orems
    -1.66
     return
    -1.65
    effectiveness
    -1.60
     entirety
    -1.57
     possibility
    -1.56
    POSITIVE LOGITS
    edia
    1.89
    atrix
    1.82
    inery
    1.79
    andel
    1.79
    orphic
    1.70
     alone
    1.70
    dB
    1.68
    waves
    1.59
    IMO
    1.56
    neh
    1.56
    Activations Density 0.105%

    No Known Activations