© 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. 28891
    Prev
    Next
    INDEX
    Explanations

    mentions of specific financial institutions or entities

    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
    221
    +0.12
    0.7%
    110
    +0.11
    0.6%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.12
    0.03
    370
    +0.11
    0.03
    265
    +0.10
    0.03
    Negative Logits
    ĵ
    -2.63
    ¿½
    -2.22
    Ĵ
    -2.15
    ¾
    -2.10
    ķ
    -1.99
    ij
    -1.97
    ĥ½
    -1.94
    ¡
    -1.94
    ł
    -1.93
    Ĥ
    -1.84
    POSITIVE LOGITS
    omething
    1.72
    sein
    1.67
    lotte
    1.66
    poons
    1.58
    dorff
    1.56
    hti
    1.55
     Square
    1.54
    able
    1.54
    wic
    1.53
     ${
    1.52
    Activations Density 0.108%

    No Known Activations