© 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. 26138
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals or people involved in a context

    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
    177
    +0.12
    0.7%
    300
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.12
    0.01
    52
    +0.12
    0.01
    177
    +0.12
    0.01
    Negative Logits
     APPEALS
    -1.52
    ).$
    -1.51
    TING
    -1.48
    ubicin
    -1.43
    bing
    -1.42
    ALTH
    -1.41
    lando
    -1.40
     COUNTY
    -1.39
    aning
    -1.39
     those
    -1.39
    POSITIVE LOGITS
    heet
    2.06
    oft
    1.89
    helf
    1.83
    sheet
    1.82
    ki
    1.81
    emente
    1.80
    etto
    1.73
    iale
    1.68
    chaft
    1.65
    amente
    1.64
    Activations Density 0.024%

    No Known Activations