© 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. 29549
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of conjugation in chemical 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
    156
    +0.17
    1.0%
    126
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.17
    0.01
    48
    +0.12
    0.01
    142
    +0.11
    0.01
    Negative Logits
     celebrated
    -1.59
     nurses
    -1.55
     Connor
    -1.48
     Eve
    -1.47
    aves
    -1.47
     dreamed
    -1.46
    ene
    -1.45
    orters
    -1.43
     Casey
    -1.40
     Wales
    -1.39
    POSITIVE LOGITS
    ULAR
    1.73
    pora
    1.71
    orno
    1.64
    flare
    1.60
    umn
    1.56
    wort
    1.55
     zone
    1.55
    IFIC
    1.52
     gaps
    1.49
     radius
    1.49
    Activations Density 0.048%

    No Known Activations