© 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. 25553
    Prev
    Next
    INDEX
    Explanations

    terms related to amplification or increase in effect or intensity

    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
    148
    +0.14
    0.8%
    376
    +0.13
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.14
    0.01
    443
    +0.13
    0.01
    422
    +0.12
    0.00
    Negative Logits
    yk
    -1.59
     reversed
    -1.59
    enson
    -1.52
    ared
    -1.50
    alty
    -1.47
    've
    -1.47
    ITC
    -1.46
    ž
    -1.45
    aked
    -1.45
    woke
    -1.44
    POSITIVE LOGITS
     ones
    1.60
     etc
    1.56
     (\>
    1.55
     please
    1.54
     envelope
    1.51
     characters
    1.49
    illo
    1.39
     productions
    1.39
     videos
    1.38
     intro
    1.38
    Activations Density 0.010%

    No Known Activations