© 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. 28696
    Prev
    Next
    INDEX
    Explanations

    references to data structures such as ArrayLists and HashMaps

    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
    376
    +0.15
    0.8%
    144
    +0.14
    0.8%
    123
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.15
    0.01
    123
    +0.14
    0.01
    324
    +0.12
    0.01
    Negative Logits
    ĵ
    -2.89
    ³
    -2.68
    Ĵ
    -2.66
    ¯
    -2.65
    ij
    -2.60
    ´
    -2.60
    ¿
    -2.41
    ¤
    -2.41
    Ĥ¬
    -2.38
    ħ
    -2.37
    POSITIVE LOGITS
     vols
    1.52
    amsbsy
    1.47
    igan
    1.47
    ison
    1.43
    erialize
    1.43
     kb
    1.40
     thereof
    1.39
    zez
    1.39
    istry
    1.38
    haus
    1.38
    Activations Density 0.011%

    No Known Activations