© 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. 23587
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographical areas

    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
    23
    +0.29
    1.7%
    474
    +0.13
    0.7%
    232
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.29
    0.09
    232
    +0.13
    0.10
    332
    +0.13
    0.10
    Negative Logits
    acea
    -1.75
    autre
    -1.67
    )|$(
    -1.62
    ÃŃa
    -1.60
    liga
    -1.59
    ución
    -1.58
    cases
    -1.57
    Ī
    -1.55
    ului
    -1.53
    Argued
    -1.50
    POSITIVE LOGITS
    ubottu
    1.44
     heart
    1.43
     nothing
    1.41
    mo
    1.41
     stomach
    1.41
     hearts
    1.40
    STEM
    1.40
    ogly
    1.39
     agarose
    1.35
     pin
    1.33
    Activations Density 0.717%

    No Known Activations