© 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. 2-MLP-SM
    11. 23834
    Prev
    Next
    INDEX
    Explanations

    references to victories in sports

    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/2-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.2.hook_mlp_out
    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
    +0.18
    1.0%
    175
    +0.13
    0.7%
    261
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.18
    0.03
    249
    +0.13
    0.03
    298
    +0.11
    0.03
    Negative Logits
     luck
    -1.62
     shape
    -1.59
     fruits
    -1.50
     loser
    -1.48
     joy
    -1.46
     winners
    -1.44
     coordination
    -1.41
    place
    -1.41
     lucky
    -1.36
    voir
    -1.36
    POSITIVE LOGITS
     TC
    1.44
     ASP
    1.43
    udes
    1.41
    arman
    1.39
     others
    1.38
     ADVIS
    1.35
     whom
    1.35
    ary
    1.35
    aries
    1.33
    ASP
    1.31
    Activations Density 0.336%

    No Known Activations