© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11233
    Prev
    Next
    INDEX
    Explanations

    references to various types of certifications and official documents

    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
    156
    +0.15
    0.8%
    251
    +0.14
    0.8%
    139
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.15
    0.03
    232
    +0.14
    0.04
    139
    +0.14
    0.03
    Negative Logits
    asmod
    -1.67
    ĨĴ
    -1.65
    urane
    -1.65
    urger
    -1.62
    hem
    -1.61
    veh
    -1.60
    omorphism
    -1.57
    erville
    -1.54
    encephal
    -1.53
    hores
    -1.53
    POSITIVE LOGITS
    ainties
    2.80
    ificates
    2.44
    ificate
    2.44
     certificate
    1.80
    iorari
    1.79
     sample
    1.74
     holders
    1.69
     document
    1.69
    ified
    1.67
    ify
    1.63
    Activations Density 0.339%

    No Known Activations