© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26493
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and optimization

    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
    168
    +0.13
    0.7%
    293
    +0.12
    0.6%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.03
    293
    +0.12
    0.03
    282
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -4.05
    Ĭ
    -3.90
     ↵
    -3.68
    č↵č↵
    -3.68
    -3.68
    ↵
    -3.68
    č↵
    -3.68
    ↵
    -3.68
    <|outofrange|>
    -3.68
    <|outofrange|>
    -3.68
    POSITIVE LOGITS
     page
    1.49
     forged
    1.46
     Page
    1.39
     PAGE
    1.35
    claimed
    1.35
    labelled
    1.31
     backing
    1.26
     parcel
    1.26
     donated
    1.24
     pledged
    1.23
    Activations Density 0.250%

    No Known Activations