© 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. 27064
    Prev
    Next
    INDEX
    Explanations

    the phrase "within 10."

    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
    71
    +0.15
    0.9%
    329
    +0.14
    0.8%
    153
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.15
    0.04
    82
    +0.14
    0.04
    112
    +0.14
    0.04
    Negative Logits
    ocrates
    -1.55
     plag
    -1.54
    ellers
    -1.51
    elt
    -1.47
    äll
    -1.47
     known
    -1.43
     equip
    -1.43
    ());
    -1.42
    elled
    -1.41
     elementary
    -1.41
    POSITIVE LOGITS
    Ļª
    2.91
    ĥ
    2.80
    ĥ½
    2.72
    ľĵ
    2.61
    ¢
    2.52
    ¼
    2.50
    ¥
    2.46
    Į
    2.45
    ¬
    2.42
    ŀ
    2.36
    Activations Density 0.023%

    No Known Activations