© 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 EvalsExportsAPI 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. 29150
    Prev
    Next
    INDEX
    Explanations

    instances of the ordinal "th" indicating a numerical position or ranking

    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
    404
    +0.15
    0.9%
    457
    +0.11
    0.6%
    211
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.05
    112
    +0.11
    0.05
    166
    +0.11
    0.04
    Negative Logits
    ¿
    -2.83
    Ĥ
    -2.77
    ¦
    -2.72
    ±
    -2.71
    Ĭ
    -2.70
    ¥
    -2.65
    Īĺ
    -2.60
    ¬
    -2.59
    ¢
    -2.56
    °
    -2.53
    POSITIVE LOGITS
    ousand
    1.77
    neys
    1.69
    ailand
    1.67
    noon
    1.61
    idden
    1.58
    resholds
    1.53
    ousands
    1.52
    assic
    1.49
    hearted
    1.45
    romes
    1.43
    Activations Density 0.037%

    No Known Activations