© 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. 27872
    Prev
    Next
    INDEX
    Explanations

    the specific term "twelve" in various contexts

    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
    156
    +0.14
    0.8%
    139
    +0.14
    0.8%
    456
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.14
    0.01
    139
    +0.14
    0.01
    307
    +0.13
    0.01
    Negative Logits
    ère
    -1.65
     Society
    -1.58
     destination
    -1.53
    orte
    -1.50
     fame
    -1.45
     necess
    -1.44
     shelf
    -1.44
     scene
    -1.40
    eer
    -1.40
    scene
    -1.39
    POSITIVE LOGITS
    Īĺ
    3.34
    ¾
    3.15
    Ļª
    2.99
    ĨĴ
    2.89
    ij
    2.85
    ¿
    2.85
    º
    2.84
    ·¸
    2.83
    ¶
    2.79
    ª
    2.74
    Activations Density 0.229%

    No Known Activations