© 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. 26989
    Prev
    Next
    INDEX
    Explanations

    specific names related to incidents and events

    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
    369
    +0.13
    0.8%
    376
    +0.13
    0.7%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.13
    0.01
    59
    +0.13
    0.01
    111
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.73
    ¿½
    -2.70
    ¢
    -2.29
    Ĥ
    -2.16
    ¼
    -2.12
    °
    -2.10
    Ń
    -2.05
    ¿
    -2.04
    »¿
    -2.03
    Ļª
    -1.97
    POSITIVE LOGITS
    wick
    1.89
    sworth
    1.67
    oto
    1.64
    ian
    1.63
    ERTY
    1.62
    aho
    1.62
    rix
    1.61
    owned
    1.58
    ei
    1.54
    ele
    1.53
    Activations Density 0.012%

    No Known Activations