© 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. 26865
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, particularly those related to medication

    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
    23
    +0.18
    1.0%
    231
    +0.12
    0.7%
    170
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.18
    0.04
    23
    +0.12
    0.03
    231
    +0.10
    0.03
    Negative Logits
    emission
    -1.47
    will
    -1.44
    VII
    -1.39
    paragraph
    -1.34
    statements
    -1.33
     Clerk
    -1.32
    isi
    -1.31
    III
    -1.31
    Kl
    -1.30
    temporal
    -1.27
    POSITIVE LOGITS
     mine
    1.83
     yours
    1.79
    1.61
    ↵  ↵
    1.61
    1.61
    ↵
    1.61
    ↵  Âł
    1.61
    č↵
    1.61
     ↵
    1.61
    č↵
    1.61
    Activations Density 0.280%

    No Known Activations