© 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. 27836
    Prev
    Next
    INDEX
    Explanations

    the term "mean" in various contexts

    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
    52
    +0.13
    0.7%
    368
    +0.12
    0.7%
    198
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.13
    0.03
    266
    +0.12
    0.03
    116
    +0.11
    0.03
    Negative Logits
    cha
    -1.78
    yn
    -1.69
    hed
    -1.69
    ub
    -1.60
    ]{.
    -1.53
    htra
    -1.51
    iers
    -1.48
    hn
    -1.48
    encies
    -1.45
    bsd
    -1.43
    POSITIVE LOGITS
    lights
    1.64
     GMT
    1.58
     identical
    1.53
     breath
    1.48
     suit
    1.46
     accompanies
    1.46
     glare
    1.45
     photographs
    1.45
     coma
    1.43
     watches
    1.42
    Activations Density 0.011%

    No Known Activations