© 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. 30071
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and object references within a sporting context

    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
    258
    +0.14
    0.8%
    376
    +0.12
    0.7%
    118
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.14
    0.01
    58
    +0.12
    0.01
    262
    +0.12
    0.01
    Negative Logits
    ľĵ
    -1.88
    ĥ½
    -1.77
    ĺ
    -1.70
    chy
    -1.68
    >';
    -1.66
     brow
    -1.62
    OOGLE
    -1.62
    £
    -1.59
    ·¸
    -1.57
    ŀ
    -1.56
    POSITIVE LOGITS
    work
    1.92
    bench
    1.85
    craft
    1.75
    aje
    1.75
    ű
    1.65
    ière
    1.61
    ifest
    1.60
    hattan
    1.60
    ruptcy
    1.58
    castle
    1.57
    Activations Density 0.010%

    No Known Activations