© 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. 0-MLP-SM
    11. 30596
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or position

    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
    156
    +0.16
    0.9%
    376
    +0.12
    0.6%
    353
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.16
    0.01
    320
    +0.12
    0.01
    311
    +0.10
    0.01
    Negative Logits
     Copyright
    -1.54
     <%=
    -1.50
    :/
    -1.48
    cer
    -1.46
     Catalog
    -1.41
    stituted
    -1.40
     dried
    -1.38
    ÄŁ
    -1.37
    Bundle
    -1.35
     copyright
    -1.32
    POSITIVE LOGITS
     poses
    1.63
    amente
    1.57
    ément
    1.56
    unov
    1.51
    imate
    1.50
    ETHOD
    1.49
    àµį
    1.45
     between
    1.42
    evin
    1.41
    ité
    1.41
    Activations Density 0.430%

    No Known Activations