© 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. 10982
    Prev
    Next
    INDEX
    Explanations

    terminology related to quantum physics and computing

    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
    +0.27
    1.6%
    142
    +0.13
    0.7%
    88
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.27
    0.01
    290
    +0.13
    0.01
    422
    +0.12
    0.01
    Negative Logits
     hers
    -1.72
    ETHOD
    -1.63
    ighs
    -1.63
    >`
    -1.62
     her
    -1.58
     ongoing
    -1.56
     entirety
    -1.53
    igh
    -1.43
     approval
    -1.42
    oser
    -1.41
    POSITIVE LOGITS
    cs
    1.68
    ty
    1.68
    meg
    1.54
    cif
    1.52
     supremacy
    1.48
     computing
    1.42
    ics
    1.42
    gold
    1.40
    fusion
    1.38
    net
    1.38
    Activations Density 0.108%

    No Known Activations