© 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. 28207
    Prev
    Next
    INDEX
    Explanations

    the term "amar"

    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
    450
    +0.12
    0.7%
    457
    +0.11
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.12
    0.01
    181
    +0.11
    0.01
    111
    +0.11
    0.01
    Negative Logits
    ij
    -2.06
    Ī
    -1.68
    ł
    -1.67
    ĸ´
    -1.66
    ĥ
    -1.64
    upiter
    -1.63
    Ŀ
    -1.59
    ĥ½
    -1.54
     ."
    -1.54
    Ĭ
    -1.54
    POSITIVE LOGITS
    uscript
    1.65
    fruit
    1.58
    nik
    1.50
    rou
    1.47
    iewicz
    1.47
     doi
    1.46
    berries
    1.45
    igated
    1.44
    witz
    1.43
    illion
    1.41
    Activations Density 0.016%

    No Known Activations