© 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 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. 29385
    Prev
    Next
    INDEX
    Explanations

    terms related to financial subjects and services

    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
    156
    +0.17
    1.0%
    406
    +0.13
    0.8%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.17
    0.02
    126
    +0.13
    0.01
    460
    +0.11
    0.01
    Negative Logits
     maternal
    -1.73
     gender
    -1.68
     gentle
    -1.60
     paternal
    -1.57
     complete
    -1.55
     sex
    -1.54
     gay
    -1.53
     measurable
    -1.53
     sexually
    -1.49
     '</
    -1.48
    POSITIVE LOGITS
    films
    1.91
    yards
    1.74
    fecture
    1.72
    amble
    1.68
    ist
    1.60
    erals
    1.58
     outlets
    1.56
     Affairs
    1.54
    plots
    1.51
     Bundes
    1.50
    Activations Density 0.010%

    No Known Activations