© 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. 2-MLP-SM
    11. 24002
    Prev
    Next
    INDEX
    Explanations

    instances of the word "assigned" and related terms indicating allocation or assignment

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    428
    +0.15
    0.8%
    172
    +0.13
    0.7%
    486
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    428
    +0.15
    0.05
    335
    +0.13
    0.06
    120
    +0.12
    0.06
    Negative Logits
    ETHOD
    -1.87
     thereof
    -1.76
    documentclass
    -1.63
     appoint
    -1.54
    dtd
    -1.46
     lt
    -1.43
     ordained
    -1.41
    nie
    -1.39
    {}{
    -1.39
    ()"
    -1.37
    POSITIVE LOGITS
    red
    1.57
     Photograph
    1.53
    uras
    1.39
     accord
    1.37
    urbed
    1.36
    Illustration
    1.32
    tico
    1.32
     ambient
    1.31
     grids
    1.31
     upside
    1.30
    Activations Density 0.802%

    No Known Activations