© 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. 4-RES-SM
    6. 11655
    Prev
    Next
    INDEX
    Explanations

    references to digital currency terms

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.17
    0.9%
    375
    +0.12
    0.7%
    249
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.17
    0.02
    437
    +0.12
    0.03
    477
    +0.11
    0.03
    Negative Logits
     suit
    -1.71
    ETHOD
    -1.56
     Interior
    -1.45
     bachelor
    -1.36
    VV
    -1.35
     seat
    -1.35
    QL
    -1.34
     graduate
    -1.33
    apor
    -1.33
     responders
    -1.31
    POSITIVE LOGITS
    terness
    3.33
    coins
    3.26
    umen
    2.88
    uminous
    2.84
    meal
    2.68
    ches
    2.62
    bucket
    2.58
    maps
    2.54
    terest
    2.52
    ters
    2.45
    Activations Density 0.246%

    No Known Activations