© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27948
    Prev
    Next
    INDEX
    Explanations

    references to a specific center or institution

    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
    +0.22
    1.3%
    343
    +0.12
    0.7%
    107
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.22
    0.02
    107
    +0.12
    0.01
    134
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.74
    ¯
    -2.00
    IJ
    -2.00
    Ĥ
    -1.98
    Ĥ¬
    -1.97
    ¥
    -1.96
    ¦
    -1.88
    §
    -1.87
    ij
    -1.84
     nothing
    -1.73
    POSITIVE LOGITS
    ycin
    1.87
    pieces
    1.86
    holm
    1.71
    ville
    1.70
    piece
    1.69
    erna
    1.69
    holder
    1.68
    ship
    1.61
    borg
    1.60
    ermost
    1.60
    Activations Density 0.013%

    No Known Activations