© 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. 25049
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities in a promotional or descriptive context

    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
    369
    +0.14
    0.8%
    123
    +0.13
    0.7%
    331
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.14
    0.05
    500
    +0.13
    0.04
    423
    +0.12
    0.06
    Negative Logits
    ero
    -1.76
    ew
    -1.74
    ef
    -1.61
     days
    -1.53
     procedural
    -1.51
     fool
    -1.50
    eded
    -1.48
    ł
    -1.43
     saf
    -1.42
    verse
    -1.37
    POSITIVE LOGITS
    lickr
    1.62
    asone
    1.60
     restraint
    1.49
    ĨĴ
    1.46
    fiddle
    1.42
    Inflater
    1.37
    )}/\
    1.35
    YLE
    1.35
    hog
    1.35
    igate
    1.34
    Activations Density 0.462%

    No Known Activations