© 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. 28846
    Prev
    Next
    INDEX
    Explanations

    references to programming languages

    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
    21
    +0.11
    0.6%
    410
    +0.11
    0.6%
    79
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.11
    0.01
    21
    +0.11
    0.01
    79
    +0.10
    0.01
    Negative Logits
    cept
    -1.81
     ](
    -1.60
    odor
    -1.57
    ?_
    -1.56
     rapid
    -1.54
    ?'
    -1.53
     scheduled
    -1.52
    _**
    -1.48
    olate
    -1.47
    '?"
    -1.47
    POSITIVE LOGITS
    cias
    1.95
    rangian
    1.93
    ppo
    1.86
    auge
    1.82
    quist
    1.82
    ariate
    1.79
    gren
    1.78
    hetto
    1.70
    ké
    1.70
    ue
    1.66
    Activations Density 0.015%

    No Known Activations