© 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. 30252
    Prev
    Next
    INDEX
    Explanations

    references to numerical quantities or statistics

    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
    +0.19
    1.0%
    477
    +0.13
    0.7%
    139
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.19
    0.13
    217
    +0.13
    0.10
    310
    +0.12
    0.10
    Negative Logits
     contention
    -1.56
    Argued
    -1.55
    oured
    -1.43
    rica
    -1.40
    polymer
    -1.39
    chers
    -1.36
    polymers
    -1.36
     anyone
    -1.35
    CHANTABILITY
    -1.35
     nobody
    -1.32
    POSITIVE LOGITS
    ĭ
    3.74
    į
    3.70
    Ĵ
    3.43
    º
    3.40
    ³
    3.32
    ¡
    3.27
    ª
    3.23
    ¶
    3.23
    ĺ
    3.17
    ļ
    3.09
    Activations Density 0.945%

    No Known Activations