© 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. 0-MLP-SM
    6. 27869
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds related to health and safety

    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
    111
    +0.13
    0.7%
    298
    +0.12
    0.7%
    314
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.13
    0.01
    300
    +0.12
    0.01
    111
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -1.94
    upon
    -1.79
    ij
    -1.73
    hes
    -1.68
    Ħ
    -1.63
    Ĺ
    -1.58
    Ļª
    -1.53
    Ī
    -1.51
    Ĥ¬
    -1.51
    itional
    -1.50
    POSITIVE LOGITS
    stown
    1.73
    \][
    1.72
    ettes
    1.59
     filings
    1.56
    "}](#
    1.55
    cone
    1.52
    +)
    1.50
    auge
    1.49
    eto
    1.46
    enos
    1.45
    Activations Density 0.461%

    No Known Activations