© 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. 30409
    Prev
    Next
    INDEX
    Explanations

    references to planning and strategy 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
    156
    +0.18
    1.1%
    376
    +0.16
    0.9%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.18
    0.02
    275
    +0.16
    0.02
    173
    +0.12
    0.02
    Negative Logits
    §
    -1.58
    zona
    -1.47
    jours
    -1.44
    ĥ½
    -1.41
     value
    -1.34
    rier
    -1.32
    SHA
    -1.32
    CUSSION
    -1.31
     StringBuilder
    -1.29
    ammar
    -1.27
    POSITIVE LOGITS
    estine
    1.73
     Parenthood
    1.67
    etes
    1.57
     instrument
    1.45
     apparatus
    1.44
    ulator
    1.41
     malf
    1.41
    ogue
    1.34
     instruments
    1.34
    crime
    1.33
    Activations Density 0.017%

    No Known Activations