© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and judgments

    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
    388
    +0.12
    0.7%
    294
    +0.11
    0.6%
    283
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.12
    0.11
    178
    +0.11
    0.12
    219
    +0.09
    0.10
    Negative Logits
    ĻĤ
    -2.29
    inating
    -1.59
    paring
    -1.51
    iating
    -1.41
    ating
    -1.40
     Summary
    -1.39
    inned
    -1.39
    proof
    -1.37
     down
    -1.36
     testify
    -1.35
    POSITIVE LOGITS
    erves
    1.79
    ()"
    1.36
     plus
    1.33
    ίαÏĤ
    1.32
     influences
    1.32
    ides
    1.32
    lichen
    1.30
    ás
    1.30
    еп
    1.28
    cern
    1.25
    Activations Density 2.493%

    No Known Activations