© 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. 30313
    Prev
    Next
    INDEX
    Explanations

    terms related to beans

    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
    94
    +0.14
    0.8%
    376
    +0.14
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.14
    0.01
    94
    +0.14
    0.01
    43
    +0.12
    0.01
    Negative Logits
    Ń
    -1.94
    ÑĤÑĮ
    -1.70
    OOGLE
    -1.59
    _**
    -1.58
    úblic
    -1.56
    ras
    -1.52
    cke
    -1.50
    ?_
    -1.49
     suppose
    -1.46
    aneously
    -1.45
    POSITIVE LOGITS
    emaker
    1.97
    quist
    1.67
    notes
    1.66
    strom
    1.62
    stalk
    1.60
     challenges
    1.60
    house
    1.58
    houses
    1.57
    elijk
    1.56
    istry
    1.54
    Activations Density 0.016%

    No Known Activations