© 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. 26930
    Prev
    Next
    INDEX
    Explanations

    terms related to primers and molecular biology techniques

    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
    20
    +0.16
    0.9%
    109
    +0.11
    0.6%
    72
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.16
    0.01
    480
    +0.11
    0.01
    111
    +0.11
    0.01
    Negative Logits
    ·
    -1.60
     any
    -1.52
    ĻĤ
    -1.51
    OY
    -1.50
    Ļª
    -1.38
     anything
    -1.37
     totality
    -1.36
     harbor
    -1.35
    ³
    -1.35
    ĨĴ
    -1.33
    POSITIVE LOGITS
    bags
    1.94
    ôt
    1.65
    resses
    1.65
    ksen
    1.59
    itives
    1.57
    bag
    1.54
    CHA
    1.51
    ressor
    1.50
    veolar
    1.48
    jah
    1.48
    Activations Density 0.027%

    No Known Activations