© 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. 25837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    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
    126
    +0.14
    0.8%
    262
    +0.12
    0.7%
    281
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.15
    26
    +0.12
    0.14
    199
    +0.12
    0.14
    Negative Logits
    ingly
    -1.82
    nae
    -1.79
    ned
    -1.74
    liest
    -1.74
    oused
    -1.64
    hest
    -1.62
     lobes
    -1.59
    thood
    -1.56
     bidding
    -1.53
     lobe
    -1.45
    POSITIVE LOGITS
    Ĭ
    2.56
    ¯
    2.55
    «
    2.48
    ¦
    2.41
    į
    2.29
    ĨĴ
    2.17
    ¨
    2.15
    Ľ
    2.14
    ¢
    2.11
    Ń
    2.11
    Activations Density 0.274%

    No Known Activations