© 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. 28636
    Prev
    Next
    INDEX
    Explanations

    formatted HTML or XML closing tags

    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
    176
    +0.12
    0.7%
    407
    +0.12
    0.7%
    247
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.12
    0.04
    176
    +0.12
    0.04
    140
    +0.12
    0.03
    Negative Logits
    ize
    -1.59
    \|\
    -1.55
    []{
    -1.52
    apsed
    -1.43
    }\}$
    -1.38
     caused
    -1.36
    izumab
    -1.35
    izing
    -1.32
    UTH
    -1.29
    keV
    -1.29
    POSITIVE LOGITS
    thead
    1.43
     Matter
    1.42
    ental
    1.41
    iece
    1.39
     colours
    1.37
    dy
    1.37
     genres
    1.35
     mind
    1.32
    ¿½
    1.32
    eric
    1.30
    Activations Density 0.022%

    No Known Activations