© 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. 24961
    Prev
    Next
    INDEX
    Explanations

    references to specific designs or design-related topics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.17
    1.0%
    376
    +0.14
    0.9%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.17
    0.01
    37
    +0.14
    0.01
    501
    +0.12
    0.01
    Negative Logits
    ÄŁ
    -1.64
     worth
    -1.53
    ÑĹ
    -1.52
     coast
    -1.50
     href
    -1.44
     grateful
    -1.43
     Angels
    -1.41
     Ale
    -1.40
     ashamed
    -1.40
     knowing
    -1.37
    POSITIVE LOGITS
    emis
    2.10
    ement
    2.09
    ensor
    2.00
    em
    1.95
    icle
    1.79
    able
    1.75
    ball
    1.74
    "}](#
    1.72
    lei
    1.69
    etting
    1.69
    Activations Density 0.012%

    No Known Activations