© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    instances of financial transactions or obligations related to payments

    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
    +0.30
    1.9%
    376
    +0.16
    1.0%
    174
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.30
    0.02
    156
    +0.16
    0.01
    147
    +0.10
    0.02
    Negative Logits
    ĥ½
    -1.97
    aleigh
    -1.81
    unts
    -1.70
     Acad
    -1.54
    leans
    -1.51
    asts
    -1.46
     myself
    -1.46
    TRODUCTION
    -1.44
     lesbian
    -1.44
    -1.40
    POSITIVE LOGITS
    onder
    1.74
    illar
    1.67
    heet
    1.67
    iment
    1.59
    emat
    1.54
    ensory
    1.53
    imensional
    1.50
    eto
    1.50
    orbent
    1.50
    Separ
    1.47
    Activations Density 0.298%

    No Known Activations