© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-MLP-SM
    11. 25086
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only."

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    17
    +0.13
    0.7%
    225
    +0.12
    0.7%
    252
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.13
    0.05
    252
    +0.12
    0.04
    318
    +0.12
    0.02
    Negative Logits
    holds
    -1.87
     agree
    -1.78
     exercise
    -1.72
     effort
    -1.65
     heed
    -1.64
     attempt
    -1.59
     advance
    -1.49
     urge
    -1.46
     tight
    -1.46
     exert
    -1.46
    POSITIVE LOGITS
    º
    2.62
    Ł
    2.37
    Į
    2.21
    ®
    2.09
    ¹
    2.05
    ª
    2.04
    ¡
    2.03
    ı
    1.99
    ´
    1.98
    ³
    1.98
    Activations Density 0.125%

    No Known Activations