© 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. 25486
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used for formatting or emphasis

    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
    505
    +0.12
    0.7%
    369
    +0.12
    0.7%
    391
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.12
    0.01
    261
    +0.12
    0.01
    505
    +0.12
    0.01
    Negative Logits
    ¨
    -1.88
    Ł
    -1.73
    ´
    -1.71
    °
    -1.63
    ·¸
    -1.61
    ¢
    -1.60
     diagram
    -1.58
    ¡
    -1.57
    OLOR
    -1.55
    »
    -1.54
    POSITIVE LOGITS
    ened
    1.64
    edly
    1.47
    ew
    1.47
    ér
    1.45
    ó
    1.42
    sight
    1.42
    PUBL
    1.41
    rá
    1.41
    woke
    1.40
    veis
    1.38
    Activations Density 0.063%

    No Known Activations