© 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. 2-MLP-SM
    11. 24021
    Prev
    Next
    INDEX
    Explanations

    licensing terms and identifiers in software documentation

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.14
    0.8%
    86
    +0.13
    0.7%
    391
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.01
    360
    +0.13
    0.01
    275
    +0.13
    0.00
    Negative Logits
    hores
    -1.56
     console
    -1.56
    ubern
    -1.50
    endas
    -1.42
    nikov
    -1.42
    References
    -1.40
     Contents
    -1.38
     References
    -1.37
    oque
    -1.37
    writers
    -1.36
    POSITIVE LOGITS
     burn
    1.56
    ized
    1.54
    ¹
    1.52
     love
    1.51
    rying
    1.46
    ittal
    1.46
     split
    1.44
     burnt
    1.43
    )].
    1.42
    pair
    1.42
    Activations Density 0.187%

    No Known Activations