© 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. 26039
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging techniques

    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
    +0.29
    1.7%
    482
    +0.12
    0.7%
    443
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.29
    0.01
    482
    +0.12
    0.01
    320
    +0.11
    0.01
    Negative Logits
    »
    -2.49
    ĥ½
    -2.36
    Ķ
    -2.19
    Ĥ¬
    -2.19
    IJ
    -2.10
    ¯
    -2.00
    ½
    -1.92
    Ĭ
    -1.90
    ĸ´
    -1.82
    ĥ
    -1.75
    POSITIVE LOGITS
    "}](#
    1.60
     area
    1.52
     amounts
    1.50
     vault
    1.49
     slots
    1.48
    ceral
    1.47
    oon
    1.45
     office
    1.43
     canal
    1.43
     slot
    1.42
    Activations Density 0.008%

    No Known Activations