© 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. 26191
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is"

    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
    158
    +0.13
    0.7%
    70
    +0.13
    0.7%
    230
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.13
    0.24
    17
    +0.13
    0.16
    233
    +0.12
    0.17
    Negative Logits
    ĨĴ
    -3.25
    Ĵ
    -2.96
    Ĥ¬
    -2.87
    Ī
    -2.85
    Īĺ
    -2.83
    ¥
    -2.81
    »
    -2.80
    ↵↵
    -2.66
    ↵
    -2.66
    -2.66
    POSITIVE LOGITS
    pires
    1.54
    autre
    1.43
     enjoys
    1.39
    astro
    1.38
     GmbH
    1.37
     area
    1.35
     exhibits
    1.34
    ords
    1.34
     whom
    1.30
     teams
    1.29
    Activations Density 0.691%

    No Known Activations