© 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. 26279
    Prev
    Next
    INDEX
    Explanations

    evidence or references indicating specific conditions or changes

    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
    +0.25
    1.5%
    156
    +0.16
    0.9%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.25
    0.01
    364
    +0.16
    0.01
    503
    +0.13
    0.01
    Negative Logits
    ĭ
    -1.79
    ĨĴ
    -1.72
    urable
    -1.64
    robe
    -1.61
    ful
    -1.53
    ows
    -1.53
     tuning
    -1.46
    rod
    -1.43
    zos
    -1.41
    raints
    -1.38
    POSITIVE LOGITS
     Parenthood
    1.55
     regularity
    1.54
     Democrat
    1.53
     customs
    1.52
     invasion
    1.40
     economy
    1.40
     allegiance
    1.39
     thicker
    1.38
     import
    1.37
    inally
    1.37
    Activations Density 0.027%

    No Known Activations