© 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. 2-MLP-SM
    11. 25588
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    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
    429
    +0.15
    0.9%
    86
    +0.15
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.15
    0.04
    277
    +0.15
    0.03
    86
    +0.14
    0.02
    Negative Logits
    CDATA
    -1.87
    olver
    -1.75
     strides
    -1.60
    oxford
    -1.56
     liter
    -1.52
    heets
    -1.51
     steps
    -1.48
    helf
    -1.48
    uel
    -1.42
    vier
    -1.42
    POSITIVE LOGITS
    aeda
    1.64
     Hockey
    1.58
     Police
    1.57
    IR
    1.55
     Patrol
    1.50
     Officers
    1.48
    rimination
    1.46
     Ont
    1.45
     Injury
    1.45
     Defendants
    1.43
    Activations Density 0.159%

    No Known Activations