© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26803
    Prev
    Next
    INDEX
    Explanations

    instances of the number 43

    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
    81
    +0.17
    1.0%
    458
    +0.16
    0.9%
    445
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.17
    0.02
    445
    +0.16
    0.02
    81
    +0.14
    0.02
    Negative Logits
     responsibility
    -1.63
    ureus
    -1.51
     least
    -1.41
     accountable
    -1.40
    rica
    -1.40
     obstruction
    -1.38
    hors
    -1.38
    river
    -1.37
    ker
    -1.35
    ocol
    -1.35
    POSITIVE LOGITS
    ³
    2.08
    µ
    2.03
    ĥ½
    1.98
    ®
    1.97
    Ĭ
    1.92
    Ń
    1.90
    ¶
    1.77
    Ľ
    1.77
    ŀ
    1.70
    Ŀ
    1.70
    Activations Density 0.019%

    No Known Activations