© 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. MLP Post
    5. 2-MLP-SM
    6. 27001
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performances

    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
    57
    +0.12
    0.6%
    222
    +0.11
    0.6%
    370
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.07
    398
    +0.11
    0.07
    278
    +0.10
    0.03
    Negative Logits
     penalty
    -1.80
     midfielder
    -1.74
     consistency
    -1.73
     upside
    -1.67
     offseason
    -1.65
     rebound
    -1.65
     tournament
    -1.62
     defender
    -1.61
     quarterback
    -1.59
     foul
    -1.56
    POSITIVE LOGITS
    linked
    1.94
    .");
    1.81
    .").
    1.76
    "].
    1.74
    )].
    1.65
    icago
    1.60
    ]."
    1.57
    )."
    1.57
    umerable
    1.55
    ties
    1.54
    Activations Density 2.538%

    No Known Activations