© 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. 2-MLP-SM
    11. 22858
    Prev
    Next
    INDEX
    Explanations

    questions asking for help or seeking information

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    334
    +0.11
    0.6%
    406
    +0.11
    0.6%
    364
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.11
    0.04
    211
    +0.11
    0.03
    334
    +0.11
    0.03
    Negative Logits
     science
    -1.61
     Science
    -1.61
     scientist
    -1.61
     NAS
    -1.52
     IDE
    -1.46
     Bad
    -1.45
    IBILITY
    -1.45
    antic
    -1.42
     administrator
    -1.41
     gods
    -1.41
    POSITIVE LOGITS
    ugin
    1.54
    haul
    1.54
    xico
    1.47
    ipel
    1.46
    eping
    1.46
     illegally
    1.45
    ugu
    1.43
    strom
    1.43
    gue
    1.40
    ygon
    1.37
    Activations Density 0.192%

    No Known Activations