© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27034
    Prev
    Next
    INDEX
    Explanations

    references to financial concepts or transactions

    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
    301
    +0.13
    0.7%
    493
    +0.12
    0.7%
    468
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.48
    98
    +0.12
    0.21
    228
    +0.11
    0.32
    Negative Logits
     Ravens
    -1.64
    rift
    -1.56
    ends
    -1.52
    ence
    -1.43
    trade
    -1.38
    isme
    -1.37
     Lions
    -1.34
    Decided
    -1.34
    rs
    -1.34
    adic
    -1.34
    POSITIVE LOGITS
     synthes
    1.58
    APDH
    1.43
    CK
    1.39
     compression
    1.39
     section
    1.36
    reon
    1.34
    inary
    1.34
     pleading
    1.34
     lumbar
    1.28
     phosphorylation
    1.26
    Activations Density 2.925%

    No Known Activations