© 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. 26099
    Prev
    Next
    INDEX
    Explanations

    specific data structure or syntax patterns in code

    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
    51
    +0.13
    0.7%
    478
    +0.13
    0.7%
    103
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.02
    411
    +0.13
    0.01
    434
    +0.11
    0.01
    Negative Logits
    hill
    -1.62
    acle
    -1.55
    igens
    -1.54
     Wells
    -1.53
    oltz
    -1.53
    asek
    -1.52
    aste
    -1.52
    afen
    -1.44
    ↵
    -1.43
    burgh
    -1.39
    POSITIVE LOGITS
     sexes
    1.66
    cule
    1.65
    iei
    1.54
    >&
    1.51
     confidence
    1.50
    *)
    1.46
     poster
    1.42
    third
    1.42
    ordinate
    1.41
    profit
    1.41
    Activations Density 1.704%

    No Known Activations