© 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. 25208
    Prev
    Next
    INDEX
    Explanations

    instances of the word "image."

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    100
    +0.17
    1.0%
    156
    +0.13
    0.7%
    377
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.17
    0.03
    196
    +0.13
    0.03
    509
    +0.13
    0.02
    Negative Logits
    ľĵ
    -2.46
    Ń
    -2.34
    IJ
    -2.21
    ³
    -2.14
    ·
    -2.13
    ĨĴ
    -2.09
    ½
    -2.07
    ¯
    -2.04
    «
    -2.01
    §
    -1.95
    POSITIVE LOGITS
    iod
    1.78
    flash
    1.60
    avat
    1.58
    reo
    1.53
    Ä
    1.50
    IMAGE
    1.47
    rist
    1.45
    isp
    1.43
     galleries
    1.42
    processing
    1.40
    Activations Density 0.080%

    No Known Activations