© 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. 0-MLP-SM
    11. 28115
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of California

    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
    182
    +0.18
    1.1%
    369
    +0.14
    0.8%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.18
    0.04
    64
    +0.14
    0.02
    28
    +0.13
    0.03
    Negative Logits
    ĥ½
    -3.01
    Ķ
    -2.87
    İ
    -2.73
    ĭ
    -2.63
    ı
    -2.61
    ¸
    -2.57
    ĩ
    -2.54
    Ħ
    -2.53
    ¶
    -2.52
    ĨĴ
    -2.50
    POSITIVE LOGITS
    leen
    1.94
    itrile
    1.78
     herself
    1.69
    imiento
    1.64
     themselves
    1.63
    \'
    1.57
    icidal
    1.55
    film
    1.54
    VERTISEMENT
    1.54
     understands
    1.53
    Activations Density 5.063%

    No Known Activations