© 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 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. 24597
    Prev
    Next
    INDEX
    Explanations

    instances of the word "controlled."

    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
    384
    +0.13
    0.7%
    347
    +0.11
    0.6%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.13
    0.02
    374
    +0.11
    0.00
    410
    +0.11
    0.01
    Negative Logits
    atics
    -1.73
    ags
    -1.52
    aton
    -1.44
    umer
    -1.43
    acs
    -1.41
     NJ
    -1.37
     ().
    -1.37
    itt
    -1.37
    $$
    -1.36
    icense
    -1.35
    POSITIVE LOGITS
    ]]>
    1.64
    urized
    1.55
    ]>
    1.54
     preempt
    1.36
    Č
    1.35
     morning
    1.34
     arbit
    1.33
     cord
    1.32
    eks
    1.31
     eye
    1.31
    Activations Density 0.212%

    No Known Activations