© 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. 25898
    Prev
    Next
    INDEX
    Explanations

    references to architects and architecture

    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
    +0.19
    1.1%
    376
    +0.13
    0.7%
    471
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.19
    0.01
    463
    +0.13
    0.01
    332
    +0.11
    0.01
    Negative Logits
    ¬
    -1.91
    §
    -1.79
    ľĵ
    -1.62
    ĥ½
    -1.57
    ĵ
    -1.55
    ij
    -1.53
    IJ
    -1.45
     current
    -1.43
    Ĥ
    -1.40
     WHETHER
    -1.38
    POSITIVE LOGITS
    urally
    2.41
    azine
    1.96
    aic
    1.83
    eous
    1.79
    ulsions
    1.68
    doms
    1.67
    igos
    1.63
    ural
    1.62
    inho
    1.62
    ics
    1.61
    Activations Density 0.008%

    No Known Activations