© 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. 30259
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal distinctions or classifications

    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
    376
    +0.12
    0.7%
    203
    +0.12
    0.7%
    457
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.12
    0.01
    213
    +0.12
    0.02
    218
    +0.11
    0.01
    Negative Logits
    upon
    -1.60
    nez
    -1.54
     pert
    -1.47
    opause
    -1.46
     myself
    -1.45
     persist
    -1.45
    ONS
    -1.42
    ku
    -1.41
     timely
    -1.39
     me
    -1.37
    POSITIVE LOGITS
    ributor
    1.75
    raction
    1.45
    ributors
    1.38
     BLAST
    1.35
    orted
    1.34
    igent
    1.34
    blind
    1.32
    ^[
    1.32
    icult
    1.29
    leneck
    1.29
    Activations Density 0.488%

    No Known Activations