© 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. 27060
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or patterns in documents

    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
    23
    +0.25
    1.6%
    478
    +0.22
    1.4%
    98
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.25
    0.26
    136
    +0.22
    0.23
    225
    +0.20
    0.23
    Negative Logits
    chart
    -1.81
     indications
    -1.72
    oft
    -1.66
    [
    -1.63
    ruptcy
    -1.61
    feld
    -1.53
    amount
    -1.49
    iot
    -1.45
    etting
    -1.45
    avier
    -1.40
    POSITIVE LOGITS
    ¼
    2.85
    ĻĤ
    2.77
    ł
    2.71
    ¿½
    2.63
    ľĵ
    2.58
    µ
    2.57
    »
    2.52
    Ĥ
    2.50
    «
    2.45
    ĥ½
    2.43
    Activations Density 16.985%

    No Known Activations