© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25258
    Prev
    Next
    INDEX
    Explanations

    specific references to consultations

    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
    +0.28
    1.7%
    376
    +0.19
    1.2%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.28
    0.01
    80
    +0.19
    0.01
    472
    +0.13
    0.01
    Negative Logits
    §
    -2.22
    ı
    -2.18
    Ĵ
    -2.17
    ĥ½
    -2.15
    ľ
    -1.98
    ķ
    -1.96
    į
    -1.92
    Ŀ
    -1.92
    ĵ
    -1.89
    ľĵ
    -1.79
    POSITIVE LOGITS
    veolar
    1.80
    ogue
    1.58
    iser
    1.57
    RAM
    1.55
    "}](#
    1.54
    oon
    1.51
    dom
    1.50
    mathchoice
    1.49
    zig
    1.48
    fty
    1.48
    Activations Density 0.050%

    No Known Activations