© 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. 0-MLP-SM
    11. 27801
    Prev
    Next
    INDEX
    Explanations

    references to previously established or current entities, agreements, or systems

    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
    420
    +0.13
    0.7%
    412
    +0.11
    0.6%
    486
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.13
    0.02
    121
    +0.11
    0.02
    463
    +0.11
    0.02
    Negative Logits
    ĺ
    -2.74
    ĻĤ
    -2.50
    Ł
    -2.47
    ľ
    -2.39
    ¡
    -2.34
    ļ
    -2.32
    Ļª
    -2.27
    IJ
    -2.25
    ¥
    -2.24
    ı
    -2.23
    POSITIVE LOGITS
    havior
    1.62
    ão
    1.60
     interface
    1.55
     others
    1.53
    poons
    1.51
    ambda
    1.50
    oles
    1.41
    ails
    1.41
    fficients
    1.40
    ribe
    1.40
    Activations Density 0.006%

    No Known Activations