© 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. 29622
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operators

    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
    23
    +0.22
    1.3%
    478
    +0.20
    1.2%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.22
    0.01
    254
    +0.20
    0.01
    373
    +0.12
    0.01
    Negative Logits
    ians
    -1.97
    LEY
    -1.82
    stand
    -1.69
    .
    -1.69
    nes
    -1.64
     oxidase
    -1.60
    rup
    -1.58
    ister
    -1.54
    icity
    -1.54
    ios
    -1.53
    POSITIVE LOGITS
    ?)
    1.65
    ``
    1.64
    ...)
    1.63
    thick
    1.63
    ldots
    1.62
     fuck
    1.58
     what
    1.56
    ?'
    1.50
     finished
    1.47
    ĻĤ
    1.47
    Activations Density 0.008%

    No Known Activations