© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    tilde characters, typically used to represent approximation or similarity

    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
    156
    +0.21
    1.2%
    333
    +0.14
    0.8%
    302
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.21
    0.03
    30
    +0.14
    0.01
    317
    +0.11
    0.03
    Negative Logits
    ĥ½
    -2.60
    ±
    -2.19
    ¦
    -2.11
    Ļª
    -2.05
    Ĥ¬
    -2.04
    °
    -1.99
    Ŀ
    -1.99
    ©
    -1.99
    ¿½
    -1.98
    ³
    -1.88
    POSITIVE LOGITS
    ches
    1.75
    vin
    1.73
    m
    1.61
    v
    1.60
    hem
    1.59
    +
    1.58
    mort
    1.56
    center
    1.50
    äs
    1.50
    -(
    1.46
    Activations Density 0.358%

    No Known Activations