© 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. 29754
    Prev
    Next
    INDEX
    Explanations

    references to possession or ownership

    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
    478
    +0.17
    1.0%
    376
    +0.15
    0.8%
    204
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.17
    0.05
    393
    +0.15
    0.04
    337
    +0.12
    0.04
    Negative Logits
    Ļª
    -3.42
    ĸ´
    -2.76
    ¨
    -2.68
    £
    -2.68
    ľ
    -2.61
    ł
    -2.60
    ĨĴ
    -2.59
    §
    -2.47
    ¡
    -2.46
    Ĺ
    -2.44
    POSITIVE LOGITS
    orkshire
    1.57
    von
    1.48
    jel
    1.47
     parental
    1.41
    wk
    1.41
    lycer
    1.38
     dealings
    1.31
     wives
    1.29
     mothers
    1.29
     fathers
    1.28
    Activations Density 1.205%

    No Known Activations