© 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. 25492
    Prev
    Next
    INDEX
    Explanations

    subjects or ideas that are considered unimportant or insignificant

    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
    376
    +0.17
    1.0%
    156
    +0.16
    0.9%
    454
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    454
    +0.17
    0.01
    19
    +0.16
    0.01
    265
    +0.14
    0.01
    Negative Logits
     predominantly
    -1.39
     separate
    -1.39
    robe
    -1.38
     tremendous
    -1.38
     utmost
    -1.35
     equal
    -1.35
     condensate
    -1.32
    ars
    -1.29
     seal
    -1.27
     complete
    -1.27
    POSITIVE LOGITS
    ĻĤ
    3.39
    £
    3.19
    ·
    3.03
    µ
    2.88
    ¬
    2.88
    º
    2.88
    ¿½
    2.85
    ¶
    2.83
    °
    2.79
    Ļª
    2.77
    Activations Density 0.013%

    No Known Activations