© 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. 29040
    Prev
    Next
    INDEX
    Explanations

    references to "raw" items or concepts

    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%
    376
    +0.16
    0.9%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.18
    0.01
    423
    +0.16
    0.01
    452
    +0.12
    0.01
    Negative Logits
    ĥ½
    -3.15
    Ń
    -3.11
    ľ
    -3.05
    ĵ
    -2.98
    ¿
    -2.96
    ľĵ
    -2.91
    Ĩ
    -2.74
    §
    -2.65
    ij
    -2.55
    ŀ
    -2.51
    POSITIVE LOGITS
    folk
    1.92
    stown
    1.74
    dock
    1.74
    lett
    1.63
    eful
    1.62
    forge
    1.62
    lings
    1.59
    shire
    1.58
    iff
    1.58
    ankind
    1.55
    Activations Density 0.014%

    No Known Activations