© 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. 26151
    Prev
    Next
    INDEX
    Explanations

    instances of the term "flip" in various contexts

    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
    376
    +0.18
    1.0%
    280
    +0.16
    0.9%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.18
    0.02
    99
    +0.16
    0.01
    59
    +0.12
    0.01
    Negative Logits
     Publ
    -1.61
    undry
    -1.50
     further
    -1.44
     Peninsula
    -1.39
     attention
    -1.39
    nez
    -1.37
     bre
    -1.36
    enderer
    -1.33
    uster
    -1.33
     Garden
    -1.32
    POSITIVE LOGITS
    heid
    1.63
    makers
    1.63
    pered
    1.60
    pocket
    1.56
    ups
    1.56
    stitutional
    1.56
    maker
    1.55
     regimes
    1.55
    hetamine
    1.48
     wrong
    1.47
    Activations Density 0.023%

    No Known Activations