© 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. 25792
    Prev
    Next
    INDEX
    Explanations

    specific sequences or patterns of characters

    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
    410
    +0.17
    0.9%
    150
    +0.14
    0.8%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.03
    150
    +0.14
    0.02
    506
    +0.13
    0.01
    Negative Logits
    aned
    -1.72
    aces
    -1.67
    aning
    -1.66
    ights
    -1.63
    acial
    -1.55
    aud
    -1.55
    ferent
    -1.49
    cens
    -1.47
     quer
    -1.45
    eing
    -1.43
    POSITIVE LOGITS
    för
    1.97
     ("
    1.75
     (“
    1.52
    card
    1.51
    cards
    1.50
    tex
    1.50
     TEX
    1.48
    ball
    1.45
     (,
    1.45
    ophone
    1.43
    Activations Density 0.020%

    No Known Activations