© 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. 26432
    Prev
    Next
    INDEX
    Explanations

    instances of the term "inflation" and related concepts

    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
    100
    +0.14
    0.8%
    474
    +0.13
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.14
    0.01
    26
    +0.13
    0.01
    100
    +0.12
    0.01
    Negative Logits
    |$.
    -2.09
    thood
    -1.96
    ciparum
    -1.90
    ))$.
    -1.90
    ].$$
    -1.86
    ristol
    -1.85
    rfloor
    -1.80
    ))=
    -1.78
    imony
    -1.74
    ]$.
    -1.74
    POSITIVE LOGITS
    ist
    2.14
    ary
    1.84
    arily
    1.73
    chart
    1.67
     controls
    1.63
    ulator
    1.58
    naire
    1.56
     accord
    1.56
     itself
    1.54
     chambers
    1.54
    Activations Density 0.015%

    No Known Activations