© 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. 23420
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week and scheduling events

    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
    252
    +0.15
    0.8%
    197
    +0.15
    0.8%
    363
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.15
    0.04
    363
    +0.15
    0.03
    196
    +0.13
    0.03
    Negative Logits
    _.
    -1.58
    ARY
    -1.55
    erne
    -1.50
    ](
    -1.50
    ...](
    -1.49
    >.
    -1.46
    aire
    -1.46
    uary
    -1.44
     accent
    -1.41
    ._
    -1.37
    POSITIVE LOGITS
    akov
    1.78
    abi
    1.44
    anton
    1.39
    imme
    1.39
    zag
    1.37
     von
    1.32
    ungen
    1.32
     Hamilton
    1.30
    taient
    1.29
     ours
    1.29
    Activations Density 0.112%

    No Known Activations