© 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. 28587
    Prev
    Next
    INDEX
    Explanations

    instances of the word "independently"

    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
    +0.11
    0.6%
    470
    +0.11
    0.6%
    165
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.01
    94
    +0.11
    0.01
    97
    +0.11
    0.01
    Negative Logits
    Ĥ¬
    -2.69
    ĵ
    -2.52
    ľĵ
    -2.51
    §
    -2.50
    Ķ
    -2.49
    ĨĴ
    -2.49
    ĺ
    -2.40
    ĸ
    -2.35
    Ŀ
    -2.33
    ĥ½
    -2.32
    POSITIVE LOGITS
    aeda
    1.69
    aires
    1.54
    essel
    1.36
    ement
    1.32
    inki
    1.32
     pon
    1.29
    noreply
    1.29
     HN
    1.25
    ôt
    1.25
    seud
    1.25
    Activations Density 0.052%

    No Known Activations