© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28110
    Prev
    Next
    INDEX
    Explanations

    instances of the "Column" keyword within a structured dataset or document context

    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
    217
    +0.12
    0.7%
    300
    +0.12
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.12
    0.01
    300
    +0.12
    0.01
    301
    +0.12
    0.01
    Negative Logits
     suppose
    -1.85
     deceased
    -1.82
     consider
    -1.64
     say
    -1.60
    radiol
    -1.60
     yours
    -1.58
     sudden
    -1.58
     harmless
    -1.56
     conceive
    -1.55
    woke
    -1.51
    POSITIVE LOGITS
     Wars
    1.78
    ist
    1.74
    gap
    1.73
    cule
    1.71
    istes
    1.71
    oon
    1.70
    âĢIJ
    1.67
    pile
    1.66
    endar
    1.66
    Box
    1.64
    Activations Density 0.011%

    No Known Activations