© 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. 26546
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Annual"

    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
    +0.22
    1.2%
    192
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.22
    0.01
    339
    +0.12
    0.01
    126
    +0.12
    0.01
    Negative Logits
    pez
    -1.66
     actors
    -1.45
    rex
    -1.43
    them
    -1.41
    vereign
    -1.33
    erc
    -1.32
    ruce
    -1.31
    ainted
    -1.31
    ž
    -1.30
    lying
    -1.30
    POSITIVE LOGITS
    "}](#
    1.70
    ized
    1.53
    iste
    1.53
    amble
    1.48
    istical
    1.47
    antry
    1.44
    opan
    1.43
    istic
    1.42
    ULAR
    1.37
    agment
    1.33
    Activations Density 0.012%

    No Known Activations