© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30455
    Prev
    Next
    INDEX
    Explanations

    instances of conversations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.28
    1.8%
    376
    +0.19
    1.2%
    365
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.28
    0.03
    466
    +0.19
    0.02
    494
    +0.16
    0.02
    Negative Logits
     penis
    -1.66
    ĥ½
    -1.54
     EPA
    -1.47
     ureth
    -1.41
     Consortium
    -1.37
    ÂĪÂij
    -1.37
     europé
    -1.35
     hydroxide
    -1.35
    ↵Č
    -1.34
    -1.34
    POSITIVE LOGITS
    alities
    1.77
    table
    1.71
    fiddle
    1.49
    ally
    1.49
    structural
    1.45
    tern
    1.45
    inqu
    1.44
     starters
    1.43
    estock
    1.43
    naire
    1.41
    Activations Density 0.015%

    No Known Activations