© 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. 29489
    Prev
    Next
    INDEX
    Explanations

    the word "who" indicating a focus on identity and relationships

    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
    114
    +0.12
    0.7%
    187
    +0.12
    0.7%
    427
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.12
    0.12
    65
    +0.12
    0.12
    106
    +0.11
    0.10
    Negative Logits
     '%
    -1.56
    ı
    -1.55
    uetooth
    -1.54
     \"
    -1.50
    axis
    -1.48
    ¢
    -1.43
    osis
    -1.43
    asis
    -1.42
    Ļª
    -1.42
    ĭ
    -1.42
    POSITIVE LOGITS
    ]]>
    1.87
    nell
    1.57
    HER
    1.54
    EMENT
    1.52
    cticut
    1.51
    ey
    1.48
     fit
    1.42
    ilant
    1.36
     behaved
    1.36
     DOM
    1.35
    Activations Density 0.110%

    No Known Activations