© 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. 30856
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "sorted"

    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
    489
    +0.13
    0.7%
    300
    +0.12
    0.7%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.01
    489
    +0.12
    0.01
    223
    +0.11
    0.01
    Negative Logits
     slightest
    -1.55
     threatened
    -1.54
    sed
    -1.50
     characterized
    -1.49
    woke
    -1.49
     bothered
    -1.47
     prevailed
    -1.47
     sustained
    -1.46
     marked
    -1.44
     hurt
    -1.43
    POSITIVE LOGITS
    ¸
    3.01
    ¤
    2.74
    ¶
    2.71
    ĻĤ
    2.71
    °
    2.70
    ¾
    2.64
    ¦
    2.62
    µ
    2.60
    ¢
    2.59
    Ĭ
    2.58
    Activations Density 0.015%

    No Known Activations