© 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. 30401
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and definitions

    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
    166
    +0.13
    0.8%
    376
    +0.12
    0.7%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.13
    0.01
    166
    +0.12
    0.01
    145
    +0.12
    0.01
    Negative Logits
    ATES
    -1.66
    idem
    -1.61
    ffer
    -1.57
    ft
    -1.48
    ater
    -1.47
    OO
    -1.45
    OTT
    -1.42
    ctors
    -1.40
    ureus
    -1.40
    abbit
    -1.40
    POSITIVE LOGITS
    iative
    1.76
     invasion
    1.61
    aceut
    1.58
    esis
    1.57
    chaft
    1.57
    veolar
    1.55
    ifiable
    1.55
     controls
    1.50
    enza
    1.45
    hardt
    1.43
    Activations Density 0.014%

    No Known Activations