© 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. 27027
    Prev
    Next
    INDEX
    Explanations

    phrases that denote ongoing actions or events

    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
    356
    +0.15
    0.9%
    292
    +0.13
    0.7%
    465
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.15
    0.06
    394
    +0.13
    0.06
    465
    +0.12
    0.06
    Negative Logits
    ¿½
    -3.17
    ĻĤ
    -3.13
    ¨
    -2.93
    Ĺ
    -2.81
    IJ
    -2.80
    Īĺ
    -2.68
    ©
    -2.67
    Ŀ
    -2.67
    ¤
    -2.57
    «
    -2.56
    POSITIVE LOGITS
    ures
    1.86
     ones
    1.69
    ainties
    1.69
    Simplify
    1.60
    ure
    1.56
    rails
    1.53
    uant
    1.47
    cery
    1.46
    forge
    1.46
    issue
    1.45
    Activations Density 0.311%

    No Known Activations