© 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. 23270
    Prev
    Next
    INDEX
    Explanations

    assertive statements about a subject's state or condition

    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
    369
    +0.13
    0.7%
    188
    +0.12
    0.7%
    492
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.13
    0.04
    81
    +0.12
    0.06
    103
    +0.11
    0.07
    Negative Logits
      ↵
    -1.76
     centre
    -1.72
    ).](
    -1.68
    respectively
    -1.51
    ]{.
    -1.33
    corner
    -1.31
    WHM
    -1.29
     same
    -1.28
     ‘
    -1.27
    oretical
    -1.26
    POSITIVE LOGITS
    heed
    1.73
    naire
    1.69
    ably
    1.64
    endas
    1.64
    ":{
    1.57
    ":"",
    1.53
     yourselves
    1.52
    iu
    1.49
    eth
    1.46
    kowski
    1.46
    Activations Density 1.189%

    No Known Activations