© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25188
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong assertions or conclusions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    96
    +0.14
    0.8%
    238
    +0.14
    0.8%
    497
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.14
    0.02
    171
    +0.14
    0.02
    354
    +0.14
    0.04
    Negative Logits
    lying
    -1.88
    iles
    -1.73
    threatening
    -1.58
     aisle
    -1.47
     whereby
    -1.45
    lets
    -1.44
     confronting
    -1.43
     planes
    -1.42
    ilities
    -1.42
     saying
    -1.42
    POSITIVE LOGITS
    issance
    1.79
     moderator
    1.55
     moder
    1.50
    apshot
    1.46
    vier
    1.46
     Garn
    1.45
    vez
    1.44
     equals
    1.43
    apine
    1.38
    ydr
    1.38
    Activations Density 0.114%

    No Known Activations