© 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. 25933
    Prev
    Next
    INDEX
    Explanations

    references to the concept of principle 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
    +0.20
    1.2%
    156
    +0.18
    1.1%
    232
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.20
    0.01
    141
    +0.18
    0.01
    132
    +0.12
    0.01
    Negative Logits
    InstanceState
    -1.56
     him
    -1.51
    ammad
    -1.48
    ène
    -1.47
     Angels
    -1.45
    ller
    -1.43
    abeth
    -1.42
     Wales
    -1.35
     Him
    -1.35
    yna
    -1.34
    POSITIVE LOGITS
    ular
    2.18
    ulos
    1.79
    fro
    1.69
    fiddle
    1.62
    sters
    1.62
    ancial
    1.56
    atics
    1.55
    imates
    1.55
    holder
    1.51
    etary
    1.51
    Activations Density 0.011%

    No Known Activations