© 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. 28673
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "list."

    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
    +0.22
    1.3%
    156
    +0.14
    0.8%
    166
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.22
    0.01
    255
    +0.14
    0.01
    241
    +0.12
    0.01
    Negative Logits
    s
    -1.96
    ses
    -1.89
    $}
    -1.63
    rapy
    -1.55
    riages
    -1.49
    ©
    -1.48
    ---|---
    -1.47
    ı
    -1.45
    ted
    -1.45
     afore
    -1.43
    POSITIVE LOGITS
    erv
    2.14
    helf
    1.90
    ucht
    1.81
    adium
    1.70
    hoe
    1.70
    ül
    1.67
    heng
    1.67
    erve
    1.66
    ong
    1.59
    osaur
    1.58
    Activations Density 0.007%

    No Known Activations