© 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. 0-MLP-SM
    6. 28278
    Prev
    Next
    INDEX
    Explanations

    concepts related to uniformity or equal treatment

    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
    404
    +0.15
    0.8%
    376
    +0.15
    0.8%
    375
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.01
    255
    +0.15
    0.01
    375
    +0.12
    0.01
    Negative Logits
    «
    -1.85
    ĥ½
    -1.80
    Č
    -1.77
    Į
    -1.73
    ogens
    -1.71
    §
    -1.66
    Ń
    -1.62
    amethasone
    -1.61
    ogen
    -1.60
    Ķ
    -1.60
    POSITIVE LOGITS
     sized
    1.43
    quist
    1.30
     PAGE
    1.29
    noreply
    1.28
     ejemplo
    1.28
    IAL
    1.27
     Fitzgerald
    1.27
     quote
    1.27
    quote
    1.26
    rette
    1.24
    Activations Density 0.005%

    No Known Activations