© 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. 30857
    Prev
    Next
    INDEX
    Explanations

    descriptors indicating thinness or lack of substance

    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
    +0.17
    0.9%
    376
    +0.16
    0.9%
    408
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.17
    0.01
    408
    +0.16
    0.01
    453
    +0.14
    0.01
    Negative Logits
    las
    -1.55
     Said
    -1.44
     Or
    -1.43
     gaze
    -1.40
     Night
    -1.37
    Drosophila
    -1.28
     Parks
    -1.27
    urs
    -1.25
    ropolis
    -1.25
     Orient
    -1.25
    POSITIVE LOGITS
    ģ
    2.54
    ŀ
    2.53
    Īĺ
    2.53
    ĻĤ
    2.40
    ¢
    2.37
    ľ
    2.29
    ij
    2.28
    Ĵ
    2.26
    ©
    2.23
    ¥
    2.17
    Activations Density 0.012%

    No Known Activations