© 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 EvalsExportsinterp-engineNEWAPI 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. 23858
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to fractions and roots

    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
    221
    +0.13
    0.7%
    364
    +0.12
    0.7%
    326
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.13
    0.02
    318
    +0.12
    0.01
    221
    +0.10
    0.01
    Negative Logits
    mouth
    -1.65
    gets
    -1.56
    cludes
    -1.52
    quartile
    -1.49
    irez
    -1.46
    FFIR
    -1.37
    slash
    -1.36
    blogger
    -1.36
    clud
    -1.35
     PubMed
    -1.34
    POSITIVE LOGITS
     frost
    1.40
     strain
    1.39
     light
    1.39
     sense
    1.36
     Hard
    1.36
     App
    1.34
    well
    1.32
    ]{.
    1.32
     weight
    1.29
    itness
    1.26
    Activations Density 0.035%

    No Known Activations