© 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. 0-MLP-SM
    11. 25524
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Avion"

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.15
    0.9%
    410
    +0.15
    0.8%
    443
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.15
    0.02
    97
    +0.15
    0.02
    332
    +0.14
    0.02
    Negative Logits
     aid
    -1.71
     interest
    -1.46
    activ
    -1.44
     ways
    -1.43
    iasis
    -1.42
    ester
    -1.40
     union
    -1.40
     why
    -1.39
     how
    -1.39
     action
    -1.38
    POSITIVE LOGITS
    ailability
    2.71
    ignon
    1.84
    Ĵ
    1.75
    ¤
    1.73
    imuth
    1.65
    illard
    1.61
    inson
    1.60
    ģ
    1.59
    illon
    1.59
    leys
    1.56
    Activations Density 0.634%

    No Known Activations