© 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. 30690
    Prev
    Next
    INDEX
    Explanations

    terms associated with billing and financial 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
    276
    +0.12
    0.7%
    443
    +0.12
    0.7%
    470
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.12
    0.01
    148
    +0.12
    0.01
    162
    +0.11
    0.01
    Negative Logits
    aliana
    -1.72
    ·¸
    -1.56
     coached
    -1.46
    ĸ´
    -1.44
    olog
    -1.39
    /#
    -1.39
     understood
    -1.39
    ikh
    -1.34
    ht
    -1.34
    hta
    -1.32
    POSITIVE LOGITS
     GOODS
    1.87
    IFF
    1.66
    hang
    1.60
    ynamic
    1.59
    à°¿
    1.58
    etect
    1.52
    rup
    1.52
    irection
    1.44
    rifug
    1.42
    eterm
    1.42
    Activations Density 0.008%

    No Known Activations