© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22550
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the status or availability of something

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    98
    +0.14
    0.8%
    487
    +0.13
    0.7%
    476
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.14
    0.02
    103
    +0.13
    0.02
    487
    +0.12
    0.02
    Negative Logits
    Ļª
    -3.22
    Ĺ
    -3.08
    ¾
    -3.04
    Ĥ
    -2.97
    ³
    -2.90
    ¯
    -2.88
    ¿½
    -2.85
    ±
    -2.84
    ł
    -2.77
    ¿
    -2.75
    POSITIVE LOGITS
    wagen
    1.69
    otec
    1.64
    ioni
    1.63
    abi
    1.61
    hed
    1.58
    anden
    1.57
    golang
    1.56
    olan
    1.51
    olis
    1.50
    endas
    1.50
    Activations Density 0.109%

    No Known Activations