© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26840
    Prev
    Next
    INDEX
    Explanations

    programming and code structures related to data handling and manipulation

    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
    +0.19
    1.1%
    271
    +0.17
    0.9%
    11
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.19
    0.17
    511
    +0.17
    0.07
    390
    +0.11
    0.06
    Negative Logits
    III
    -1.56
    cedes
    -1.55
    hao
    -1.52
    ---|---|---
    -1.51
    etta
    -1.46
    FPar
    -1.45
    hei
    -1.42
    ego
    -1.42
    VII
    -1.41
    yne
    -1.38
    POSITIVE LOGITS
    ably
    1.61
    ĻĤ
    1.60
    rolling
    1.52
    ¿½
    1.44
     foods
    1.39
    Ļª
    1.37
    URAL
    1.33
     postpartum
    1.33
     readable
    1.31
     clothing
    1.31
    Activations Density 4.107%

    No Known Activations