© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30335
    Prev
    Next
    INDEX
    Explanations

    the word "similar" and its variations in context

    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
    392
    +0.18
    1.0%
    376
    +0.13
    0.7%
    285
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.18
    0.03
    14
    +0.13
    0.03
    431
    +0.11
    0.03
    Negative Logits
    º
    -3.20
    Ľ
    -2.95
    »
    -2.82
    ¼
    -2.82
    ľĵ
    -2.78
    Ļ
    -2.70
    ·¸
    -2.67
    Ł
    -2.66
    ®
    -2.66
    ³
    -2.63
    POSITIVE LOGITS
    ities
    2.04
    ität
    1.81
    izes
    1.71
    ism
    1.65
     happens
    1.65
    ity
    1.59
    izing
    1.57
     numbers
    1.56
    Exchange
    1.52
    idades
    1.52
    Activations Density 0.971%

    No Known Activations