© 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. 26339
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal 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/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
    277
    +0.15
    0.8%
    44
    +0.14
    0.8%
    191
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.15
    0.49
    56
    +0.14
    0.17
    203
    +0.13
    0.38
    Negative Logits
    ¿½
    -2.94
    ĥ
    -2.79
    ĵ
    -2.66
    į
    -2.65
    ij
    -2.61
    Ł
    -2.59
    ±
    -2.57
    ĺ
    -2.56
    ©
    -2.44
    Ħ
    -2.44
    POSITIVE LOGITS
     against
    1.51
     apart
    1.49
     slog
    1.45
     ratings
    1.44
     innings
    1.44
     complaints
    1.40
     coverage
    1.36
    raf
    1.33
    esan
    1.32
     reli
    1.31
    Activations Density 3.915%

    No Known Activations