© 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. 28392
    Prev
    Next
    INDEX
    Explanations

    the action of understanding or explaining meanings

    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
    +0.21
    1.2%
    376
    +0.20
    1.1%
    148
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.21
    0.01
    392
    +0.20
    0.02
    266
    +0.19
    0.01
    Negative Logits
     fois
    -1.56
    ]>
    -1.54
    >();
    -1.52
    ori
    -1.48
    brahim
    -1.47
    lam
    -1.45
    sole
    -1.43
    uten
    -1.42
     premiums
    -1.41
    ż
    -1.41
    POSITIVE LOGITS
    ¨
    2.07
    °
    2.06
    enses
    1.91
    £
    1.86
    Īĺ
    1.84
    ©
    1.83
    ¢
    1.82
    ¿½
    1.74
    ¦
    1.69
    ense
    1.68
    Activations Density 0.037%

    No Known Activations