© 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. 30458
    Prev
    Next
    INDEX
    Explanations

    the word "Each" indicating repetition or stepwise content

    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
    224
    +0.13
    0.7%
    117
    +0.13
    0.7%
    388
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.13
    0.02
    388
    +0.13
    0.02
    224
    +0.12
    0.02
    Negative Logits
    ffffffff
    -1.60
     altogether
    -1.57
    ffff
    -1.55
     equivalents
    -1.33
     Experimental
    -1.29
     premie
    -1.28
     itself
    -1.27
    ticos
    -1.25
     bosons
    -1.25
     directors
    -1.24
    POSITIVE LOGITS
    ries
    1.75
    ied
    1.70
    lane
    1.66
    lasses
    1.64
    estry
    1.60
    wise
    1.58
    anna
    1.50
    rica
    1.49
    ryst
    1.48
    sen
    1.47
    Activations Density 0.028%

    No Known Activations