© 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. 27782
    Prev
    Next
    INDEX
    Explanations

    mentions of injuries or accidents involving individuals, particularly in the context of entertainment or performance

    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
    98
    +0.15
    0.9%
    365
    +0.13
    0.7%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.15
    0.40
    53
    +0.13
    0.42
    56
    +0.11
    0.11
    Negative Logits
    ingale
    -1.66
    isance
    -1.66
    vel
    -1.54
     pleth
    -1.47
    pendicular
    -1.42
    ternal
    -1.41
    ry
    -1.37
    yset
    -1.35
    -1.34
    vertisement
    -1.31
    POSITIVE LOGITS
    ŀ
    2.74
    ĻĤ
    2.71
    ³
    2.59
    »¿
    2.59
    Ł
    2.50
    ↵
    2.46
    ↵  ↵
    2.46
    ↵
    2.46
         ↵
    2.46
    č↵
    2.46
    Activations Density 4.670%

    No Known Activations