© 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. 2-MLP-SM
    11. 22726
    Prev
    Next
    INDEX
    Explanations

    Java programming language references and syntax

    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
    +0.13
    0.7%
    190
    +0.12
    0.6%
    172
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.02
    56
    +0.12
    0.03
    181
    +0.12
    0.03
    Negative Logits
    ugu
    -1.51
     pills
    -1.51
     prescriptions
    -1.49
     randomly
    -1.49
     owns
    -1.45
     hadn
    -1.45
     generations
    -1.43
     hers
    -1.43
     ones
    -1.42
    heets
    -1.41
    POSITIVE LOGITS
    ."_
    1.83
    ker
    1.79
    mit
    1.75
    lift
    1.68
    achment
    1.65
    ACK
    1.56
    mare
    1.55
    to
    1.53
    bbe
    1.53
    ught
    1.49
    Activations Density 0.363%

    No Known Activations