© 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. 27040
    Prev
    Next
    INDEX
    Explanations

    references to groups or gatherings of people, particularly in contexts involving mob behavior

    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
    376
    +0.14
    0.8%
    501
    +0.13
    0.8%
    407
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.14
    0.02
    342
    +0.13
    0.01
    407
    +0.13
    0.01
    Negative Logits
    >';
    -1.80
     virgin
    -1.68
    TRODUCTION
    -1.51
     mass
    -1.45
     Kiss
    -1.44
    '?"
    -1.44
     mean
    -1.43
     Matthews
    -1.43
     Bureau
    -1.43
    mes
    -1.43
    POSITIVE LOGITS
    ģ
    3.83
    ²
    3.43
    ī
    3.22
    ĨĴ
    3.11
    Ī
    3.10
    ¾
    2.95
    Īĺ
    2.94
    ®
    2.93
    ĩ
    2.92
    Ĵ
    2.91
    Activations Density 0.020%

    No Known Activations