© 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. 22794
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or names related to places and professional entities

    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
    269
    +0.17
    1.0%
    497
    +0.13
    0.7%
    153
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.17
    0.04
    504
    +0.13
    0.01
    332
    +0.12
    0.07
    Negative Logits
    .’
    -1.84
    oust
    -1.82
    onian
    -1.78
    ‘
    -1.69
    mouth
    -1.68
    ’.
    -1.64
    .’”
    -1.58
     contrary
    -1.56
    lights
    -1.54
    agne
    -1.52
    POSITIVE LOGITS
    «
    3.11
    ĨĴ
    2.74
    ł
    2.54
    ŀ
    2.50
    ĩ
    2.41
    ª
    2.41
    £
    2.40
    ¢
    2.40
    ¿½
    2.36
    §
    2.35
    Activations Density 1.780%

    No Known Activations