© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    the term "prevalent" in various contexts

    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
    +0.34
    2.0%
    376
    +0.20
    1.2%
    148
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.34
    0.01
    156
    +0.20
    0.01
    347
    +0.17
    0.01
    Negative Logits
    že
    -1.33
    ctomy
    -1.31
    ť
    -1.29
     expert
    -1.28
    aned
    -1.25
    ва
    -1.23
     certified
    -1.23
    docs
    -1.21
    ians
    -1.21
    walks
    -1.20
    POSITIVE LOGITS
    Ģ
    2.73
    ĻĤ
    2.64
    ĩ
    2.53
    µ
    2.51
    °
    2.50
    ¤
    2.48
    ²
    2.37
    ł
    2.25
    Ļª
    2.24
    ĥ
    2.19
    Activations Density 0.015%

    No Known Activations