© 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. 23751
    Prev
    Next
    INDEX
    Explanations

    references to national standards or qualifications

    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
    234
    +0.12
    0.6%
    466
    +0.12
    0.6%
    372
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.01
    372
    +0.12
    0.01
    90
    +0.11
    0.01
    Negative Logits
    iral
    -1.69
    áĥĶ
    -1.60
    atz
    -1.57
    ittest
    -1.54
    liament
    -1.49
    ibo
    -1.46
    úblic
    -1.46
    àµį
    -1.44
    estial
    -1.44
    irtual
    -1.40
    POSITIVE LOGITS
     objection
    1.50
     Dana
    1.43
    usted
    1.42
    OVER
    1.41
     thereafter
    1.39
    planation
    1.38
     (.
    1.35
     afterward
    1.32
     Rum
    1.31
     _(
    1.31
    Activations Density 0.175%

    No Known Activations