© 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 EvalsExportsAPI 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. 24657
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to hierarchical structure in web development

    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
    156
    +0.25
    1.4%
    305
    +0.13
    0.7%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.25
    0.01
    317
    +0.13
    0.02
    305
    +0.12
    0.01
    Negative Logits
    esty
    -1.62
    watson
    -1.50
     yourselves
    -1.40
    eLife
    -1.36
    grounds
    -1.31
    asone
    -1.30
    Publisher
    -1.27
    rfloor
    -1.27
    ões
    -1.27
    factor
    -1.25
    POSITIVE LOGITS
     ([@
    1.85
    soever
    1.43
     plans
    1.39
    abouts
    1.37
     entire
    1.35
     \[[@
    1.34
     nearer
    1.32
     responsibility
    1.28
     farther
    1.27
     Inspector
    1.26
    Activations Density 0.134%

    No Known Activations