© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26843
    Prev
    Next
    INDEX
    Explanations

    HTML tags and document structure elements

    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
    49
    +0.14
    0.8%
    68
    +0.11
    0.6%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.14
    0.02
    495
    +0.11
    0.02
    414
    +0.11
    0.01
    Negative Logits
    ½
    -1.95
    ameter
    -1.85
    ľĵ
    -1.79
    ļ
    -1.68
    aneous
    -1.65
    §
    -1.61
    IJ
    -1.57
    Ĭ
    -1.57
    ĨĴ
    -1.56
    ÃĥÃĤÃĥÃĤ
    -1.56
    POSITIVE LOGITS
     theat
    1.54
     theaters
    1.38
    rio
    1.32
    esa
    1.30
    Estim
    1.30
     sal
    1.29
     boil
    1.26
    erent
    1.26
     Observatory
    1.25
    es
    1.25
    Activations Density 0.149%

    No Known Activations