© 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. 29756
    Prev
    Next
    INDEX
    Explanations

    references to flagship products or initiatives

    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
    156
    +0.16
    0.9%
    376
    +0.13
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.16
    0.01
    149
    +0.13
    0.01
    59
    +0.12
    0.01
    Negative Logits
    awn
    -1.86
    uten
    -1.84
    anie
    -1.61
    ander
    -1.57
    ako
    -1.52
    ighed
    -1.47
    dz
    -1.45
    nd
    -1.43
    Äħ
    -1.38
    ockey
    -1.38
    POSITIVE LOGITS
    Īĺ
    2.00
    ĥ
    1.99
    Ģ
    1.91
    aments
    1.73
     letters
    1.69
     strengths
    1.65
    ¿½
    1.65
    Į
    1.59
    ľĵ
    1.57
    isms
    1.55
    Activations Density 0.018%

    No Known Activations