© 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. 0-MLP-SM
    11. 26712
    Prev
    Next
    INDEX
    Explanations

    the term "vast," indicating a focus on the concept of large scale or extent

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.14
    0.8%
    467
    +0.14
    0.8%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.14
    0.02
    254
    +0.14
    0.02
    180
    +0.12
    0.02
    Negative Logits
    rile
    -1.65
     Filed
    -1.51
     Department
    -1.45
    +}
    -1.37
    ème
    -1.37
    default
    -1.35
    arer
    -1.30
    sis
    -1.30
    lam
    -1.29
    zos
    -1.29
    POSITIVE LOGITS
    ª
    4.42
    ģ
    4.36
    ©
    4.31
    ķ
    4.28
    ŀ
    4.27
    ł
    4.24
    ¿½
    4.23
    £
    4.21
    Īĺ
    4.17
    ľĵ
    4.15
    Activations Density 0.232%

    No Known Activations