© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25696
    Prev
    Next
    INDEX
    Explanations

    references to figures, diagrams, or illustrations used in documents

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.16
    0.9%
    294
    +0.11
    0.6%
    47
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.16
    0.01
    417
    +0.11
    0.02
    184
    +0.11
    0.01
    Negative Logits
    Į
    -2.54
    »¿
    -2.05
    IJ
    -1.91
    ↵
    -1.85
           ↵
    -1.85
    ↵↵
    -1.85
    ↵↵↵
    -1.85
    -1.85
    ↵
    -1.85
    ↵
    -1.85
    POSITIVE LOGITS
    ton
    1.62
     approximate
    1.56
     emphasis
    1.51
     infusion
    1.46
     contrasted
    1.42
     contrast
    1.39
     attachment
    1.37
     opaque
    1.37
     tone
    1.35
     attachments
    1.34
    Activations Density 0.088%

    No Known Activations