© 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. 22576
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomical characteristics of stars and galaxies

    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
    408
    +0.12
    0.6%
    472
    +0.11
    0.6%
    1
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.12
    0.08
    168
    +0.11
    0.05
    306
    +0.11
    0.04
    Negative Logits
    umbing
    -1.58
     consecutive
    -1.51
     wall
    -1.44
    irable
    -1.43
    ensions
    -1.42
    arp
    -1.39
    umm
    -1.36
    )–(
    -1.35
    wall
    -1.34
    rifug
    -1.34
    POSITIVE LOGITS
    ī
    4.56
    «
    4.19
    Ń
    4.10
    Ĩ
    4.07
    ±
    4.04
    Ĭ
    4.04
    Ĥ
    4.03
    ı
    4.00
    ¼
    3.99
    »
    3.98
    Activations Density 1.768%

    No Known Activations