© 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. 29665
    Prev
    Next
    INDEX
    Explanations

    references to empty or unoccupied states or objects

    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
    376
    +0.14
    0.8%
    156
    +0.13
    0.7%
    490
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.14
    0.02
    490
    +0.13
    0.02
    326
    +0.13
    0.02
    Negative Logits
    icki
    -1.54
    ---|---
    -1.52
    yon
    -1.47
    ya
    -1.38
     daÃŁ
    -1.36
     converge
    -1.35
    yla
    -1.33
    Os
    -1.32
     Excellence
    -1.32
    ila
    -1.32
    POSITIVE LOGITS
    ł
    2.41
    ª
    2.30
    µ
    2.27
    ¸
    2.26
    ĻĤ
    2.08
    £
    2.03
    º
    2.00
    ¹
    1.97
    Ģ
    1.96
    ¤
    1.94
    Activations Density 0.333%

    No Known Activations