© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28262
    Prev
    Next
    INDEX
    Explanations

    references to specific projects

    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
    435
    +0.13
    0.8%
    48
    +0.12
    0.7%
    16
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.13
    0.02
    48
    +0.12
    0.02
    16
    +0.12
    0.02
    Negative Logits
     suppose
    -1.92
     why
    -1.84
     yours
    -1.74
    ights
    -1.73
     consider
    -1.70
    iginally
    -1.65
     want
    -1.52
     its
    -1.50
     hers
    -1.49
     apply
    -1.46
    POSITIVE LOGITS
    ¾
    2.63
    ĻĤ
    2.48
    ĸ
    2.11
    enstein
    2.03
    »¿
    2.00
    ↵
    1.99
     ↵
    1.99
    1.99
    1.99
    1.99
    Activations Density 0.015%

    No Known Activations