© 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. 29417
    Prev
    Next
    INDEX
    Explanations

    the word "considered" in various contexts

    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
    376
    +0.16
    0.9%
    148
    +0.12
    0.7%
    355
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.16
    0.02
    331
    +0.12
    0.02
    355
    +0.12
    0.03
    Negative Logits
    weet
    -1.66
    ercase
    -1.59
    suppl
    -1.56
    ened
    -1.54
    ries
    -1.54
    ashi
    -1.52
    oken
    -1.51
    dered
    -1.49
    shaw
    -1.49
    rit
    -1.48
    POSITIVE LOGITS
    ¢
    2.09
    ¼
    1.97
    ©
    1.95
    Ĥ¬
    1.92
    Īĺ
    1.75
    ¹
    1.74
    ¤
    1.74
    ł
    1.73
    ĸ
    1.73
    ĸ´
    1.69
    Activations Density 0.342%

    No Known Activations