© 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. 30299
    Prev
    Next
    INDEX
    Explanations

    references to specific terms related to coding or mathematical 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
    260
    +0.14
    0.8%
    376
    +0.13
    0.7%
    330
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.14
    0.01
    260
    +0.13
    0.01
    111
    +0.12
    0.01
    Negative Logits
    »¿
    -2.11
    ĥ
    -2.03
    Ĥ
    -2.01
    Īĺ
    -1.98
    Ĥ¬
    -1.89
     latter
    -1.82
    )$)
    -1.80
    «
    -1.78
    Ĺ
    -1.76
     knees
    -1.71
    POSITIVE LOGITS
    arian
    1.77
    ères
    1.76
    asek
    1.74
    eto
    1.73
    borne
    1.71
    heim
    1.69
    estock
    1.69
    istical
    1.68
    FW
    1.66
    endor
    1.65
    Activations Density 0.008%

    No Known Activations