© 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. 27075
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations

    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
    156
    +0.16
    0.9%
    150
    +0.15
    0.9%
    388
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.16
    0.03
    202
    +0.15
    0.03
    61
    +0.13
    0.03
    Negative Logits
    "}\].
    -1.59
    amental
    -1.54
     purposes
    -1.53
    )\]
    -1.53
    ocene
    -1.52
    ameters
    -1.49
    )\].
    -1.49
    erals
    -1.47
    ases
    -1.46
    ipher
    -1.43
    POSITIVE LOGITS
    Ĩ
    1.96
     loud
    1.84
    ®
    1.68
    voice
    1.60
    ±
    1.60
    ·
    1.54
    ´
    1.52
    nee
    1.48
    ¶
    1.48
    who
    1.47
    Activations Density 0.025%

    No Known Activations