© 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. 30082
    Prev
    Next
    INDEX
    Explanations

    instances of the word "upgrade" and its variations

    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
    148
    +0.15
    0.9%
    327
    +0.13
    0.7%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.15
    0.01
    327
    +0.13
    0.01
    94
    +0.13
    0.01
    Negative Logits
    rene
    -1.82
    omorphisms
    -1.79
    ĨĴ
    -1.74
    iler
    -1.72
    lla
    -1.71
     visited
    -1.62
    yd
    -1.59
    lene
    -1.58
    liest
    -1.58
     least
    -1.55
    POSITIVE LOGITS
    ivable
    1.54
     versions
    1.45
    IBLE
    1.42
    uary
    1.42
    opan
    1.39
    feit
    1.36
     version
    1.36
    ¶
    1.34
     taxes
    1.33
     positions
    1.32
    Activations Density 0.630%

    No Known Activations