© 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. 26430
    Prev
    Next
    INDEX
    Explanations

    mentions of events

    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
    301
    +0.14
    0.8%
    376
    +0.14
    0.8%
    117
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.14
    0.01
    117
    +0.14
    0.01
    287
    +0.11
    0.01
    Negative Logits
    ĥ½
    -3.15
    §
    -3.03
    Ĭ
    -2.73
    ¿½
    -2.70
    Ń
    -2.59
    ¸
    -2.50
    ı
    -2.50
    ´
    -2.49
    ¤
    -2.48
    ·
    -2.46
    POSITIVE LOGITS
    manship
    2.41
    pace
    2.13
    uelle
    2.02
    hip
    1.97
    bridge
    1.97
    pot
    1.96
    ional
    1.96
    mith
    1.95
    hift
    1.94
    chaft
    1.91
    Activations Density 0.016%

    No Known Activations