© 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. MLP Post
    9. 2-MLP-SM
    11. 25680
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts reflecting connections or comparisons

    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
    50
    +0.13
    0.7%
    218
    +0.12
    0.7%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.13
    0.07
    452
    +0.12
    0.04
    78
    +0.11
    0.05
    Negative Logits
     proposed
    -1.53
    ());
    -1.51
    ivia
    -1.48
    thems
    -1.47
    ()">
    -1.42
     matters
    -1.40
    TestCase
    -1.39
    ('#
    -1.34
    vertis
    -1.32
     provisions
    -1.32
    POSITIVE LOGITS
    ģ
    3.03
    Ŀ
    2.80
    ¤
    2.78
    °
    2.72
    ©
    2.67
    ¿
    2.66
    Ļ
    2.64
    ŀ
    2.64
    ¿½
    2.62
    ↵
    2.62
    Activations Density 0.607%

    No Known Activations