© 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. 23932
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "ane"

    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
    257
    +0.13
    0.8%
    23
    +0.13
    0.7%
    70
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.04
    332
    +0.13
    0.06
    306
    +0.12
    0.04
    Negative Logits
    landers
    -1.63
    rooms
    -1.51
    ero
    -1.51
     nearer
    -1.51
     itself
    -1.42
     elsewhere
    -1.42
    icians
    -1.41
     medalists
    -1.41
     whom
    -1.40
     beyond
    -1.40
    POSITIVE LOGITS
    Ħ
    3.10
    Ĵ
    3.00
    Ĥ
    2.93
    º
    2.83
    ¹
    2.82
    Į
    2.81
    Ĩ
    2.75
    °
    2.73
      ↵
    2.73
    2.73
    Activations Density 0.737%

    No Known Activations