© 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. 24097
    Prev
    Next
    INDEX
    Explanations

    references to rivers and water bodies

    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
    278
    +0.12
    0.7%
    23
    +0.12
    0.7%
    344
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.02
    344
    +0.12
    0.03
    278
    +0.11
    0.01
    Negative Logits
    rias
    -1.83
    rio
    -1.75
    waters
    -1.57
    oire
    -1.56
     duties
    -1.49
     Judiciary
    -1.42
     että
    -1.42
    agua
    -1.40
    rios
    -1.38
     (.
    -1.38
    POSITIVE LOGITS
     careful
    1.55
    osine
    1.53
    ympt
    1.51
    ologist
    1.50
     elbows
    1.50
     trier
    1.47
     blob
    1.44
    athing
    1.43
    pite
    1.42
     randomised
    1.39
    Activations Density 0.299%

    No Known Activations