© 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. 25529
    Prev
    Next
    INDEX
    Explanations

    specific sequences and patterns in structured data such as lists or codes

    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
    +0.23
    1.3%
    77
    +0.12
    0.7%
    385
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.23
    0.14
    46
    +0.12
    0.10
    77
    +0.10
    0.05
    Negative Logits
    »
    -2.18
    £
    -2.13
    Ń
    -2.08
     ↵
    -2.02
    ↵
    -2.02
    ↵
    -2.02
    ↵↵
    -2.02
    ↵
    -2.02
    ↵
    -2.02
    č↵
    -2.02
    POSITIVE LOGITS
    nae
    1.57
    landers
    1.39
    birds
    1.33
    ner
    1.33
     imagine
    1.28
    hing
    1.27
    ounded
    1.24
     suburbs
    1.24
    degree
    1.23
    etheless
    1.21
    Activations Density 3.808%

    No Known Activations