© 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. 29757
    Prev
    Next
    INDEX
    Explanations

    references to a specific class or component named "Foo"

    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
    +0.18
    1.0%
    369
    +0.16
    0.9%
    376
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.18
    0.01
    34
    +0.16
    0.01
    413
    +0.15
    0.01
    Negative Logits
    ľ
    -2.55
    ĵ
    -2.54
    ľĵ
    -2.27
    ı
    -2.21
    Ļ
    -2.20
    Ĩ
    -2.18
    ij
    -2.08
    Ń
    -2.02
    ¿
    -1.98
    ĩ
    -1.97
    POSITIVE LOGITS
    mania
    1.73
    ford
    1.72
    aho
    1.69
    hold
    1.64
    zol
    1.64
     career
    1.62
     era
    1.61
    fight
    1.58
    reng
    1.58
    lei
    1.54
    Activations Density 0.015%

    No Known Activations