© 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. 26549
    Prev
    Next
    INDEX
    Explanations

    mentions of academic titles or roles, particularly "Professor."

    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
    +0.17
    1.0%
    91
    +0.11
    0.7%
    479
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.17
    0.02
    357
    +0.11
    0.01
    86
    +0.11
    0.01
    Negative Logits
    Ļª
    -4.88
    ¬
    -4.84
    ĥ½
    -4.77
    ĨĴ
    -4.48
    Ń
    -4.45
       ↵
    -4.27
     ↵
    -4.27
    ↵
    -4.27
    -4.27
    ↵
    -4.27
    POSITIVE LOGITS
    tons
    1.76
    yard
    1.68
    lings
    1.63
    pole
    1.61
    grams
    1.59
     Hut
    1.47
    gery
    1.47
    fiddle
    1.46
     quarters
    1.43
     (>
    1.41
    Activations Density 0.010%

    No Known Activations