© 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. 25618
    Prev
    Next
    INDEX
    Explanations

    conditional phrases emphasizing exceptions or requirements

    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
    316
    +0.13
    0.7%
    248
    +0.10
    0.6%
    174
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.01
    194
    +0.10
    0.01
    366
    +0.10
    0.01
    Negative Logits
     track
    -1.82
     tracks
    -1.72
     glance
    -1.50
    ---|---
    -1.48
    ately
    -1.48
    anted
    -1.44
    atically
    -1.44
     like
    -1.44
    ands
    -1.41
     imagine
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.86
    Ļª
    2.66
    ¤
    2.22
    ¾
    1.99
    ģ
    1.94
    ĨĴ
    1.94
    Ĩ
    1.92
    Ļ
    1.86
    µ
    1.86
    ł
    1.83
    Activations Density 0.011%

    No Known Activations