© 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. 27122
    Prev
    Next
    INDEX
    Explanations

    nouns or proper names related to people and places

    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
    427
    +0.17
    1.0%
    353
    +0.14
    0.8%
    326
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.17
    0.06
    353
    +0.14
    0.05
    326
    +0.14
    0.03
    Negative Logits
    º
    -2.02
    ĥ½
    -1.79
    »¿
    -1.79
    ÃŃs
    -1.73
    ½
    -1.71
    ().
    -1.62
    cript
    -1.60
    pone
    -1.55
    verte
    -1.54
    į
    -1.54
    POSITIVE LOGITS
     kad
    1.46
    dash
    1.43
     nails
    1.36
    MODULE
    1.34
    noreply
    1.32
     onwards
    1.29
     thro
    1.29
     states
    1.28
     also
    1.27
    arus
    1.26
    Activations Density 0.369%

    No Known Activations