© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28178
    Prev
    Next
    INDEX
    Explanations

    terms related to encoding and data processing

    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
    +0.16
    0.9%
    283
    +0.14
    0.8%
    308
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.16
    0.01
    283
    +0.14
    0.02
    462
    +0.11
    0.01
    Negative Logits
    opause
    -1.78
    oned
    -1.54
    uku
    -1.53
    ActivityThread
    -1.50
    Expand
    -1.42
    je
    -1.37
     seu
    -1.37
    ague
    -1.36
    dra
    -1.34
    ––––––––
    -1.34
    POSITIVE LOGITS
     languages
    1.69
    IFIC
    1.66
    ious
    1.59
     fusion
    1.58
     styles
    1.54
     variants
    1.54
    entric
    1.53
     ears
    1.53
     style
    1.51
     anonymity
    1.51
    Activations Density 0.069%

    No Known Activations