© 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. 30623
    Prev
    Next
    INDEX
    Explanations

    empty or null values in the text

    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
    100
    +0.14
    0.8%
    494
    +0.13
    0.7%
    456
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.14
    0.01
    66
    +0.13
    0.01
    456
    +0.11
    0.01
    Negative Logits
     dehydrogenase
    -1.54
     close
    -1.52
     ([
    -1.45
    arden
    -1.43
     development
    -1.39
     phosphate
    -1.34
    obacteria
    -1.33
     reductase
    -1.32
    ometh
    -1.32
    ipel
    -1.32
    POSITIVE LOGITS
    ĩ
    3.32
    Ļª
    3.09
    ĺ
    2.82
    ľ
    2.69
    ĥ½
    2.56
    Ļ
    2.56
    ¥
    2.52
    Ŀ
    2.52
    ļ
    2.49
    µ
    2.48
    Activations Density 0.387%

    No Known Activations