© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25303
    Prev
    Next
    INDEX
    Explanations

    the concept of "absolute" or "absolute conditions."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.17
    0.9%
    213
    +0.13
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.17
    0.02
    506
    +0.13
    0.01
    299
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -2.67
    Ķ
    -2.29
    »
    -2.15
    Ĵ
    -2.06
    ½
    -2.02
    ª
    -2.00
    Ĥ¬
    -2.00
    ®
    -1.98
    Ń
    -1.89
    ĵ
    -1.84
    POSITIVE LOGITS
     basis
    1.86
     bases
    1.71
     duties
    1.64
     liberties
    1.57
    itud
    1.52
    ified
    1.49
     footing
    1.48
     reserves
    1.48
    idad
    1.47
     deposit
    1.37
    Activations Density 0.019%

    No Known Activations