© 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. 26038
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with identity systems and data management

    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
    246
    +0.12
    0.7%
    317
    +0.12
    0.7%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.36
    23
    +0.12
    0.31
    494
    +0.12
    0.24
    Negative Logits
    ired
    -1.55
     analysts
    -1.54
    ÅŁ
    -1.48
     authors
    -1.47
     Synd
    -1.43
     Tensor
    -1.39
    ictions
    -1.34
    ruptcy
    -1.34
     Conclusions
    -1.33
     tweets
    -1.32
    POSITIVE LOGITS
    die
    1.82
    Īĺ
    1.79
    Ļª
    1.74
    áĢº
    1.73
    ¹
    1.69
    º
    1.57
    ħ
    1.56
    à°¿
    1.52
    Ĵ
    1.50
    dies
    1.50
    Activations Density 3.307%

    No Known Activations