© 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 EvalsExportsAPI 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. 29322
    Prev
    Next
    INDEX
    Explanations

    references to the concept of accuracy

    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
    +0.13
    0.8%
    274
    +0.11
    0.7%
    72
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    0.02
    271
    +0.11
    0.01
    53
    +0.11
    0.03
    Negative Logits
    aka
    -1.69
     Marriage
    -1.65
    lla
    -1.60
     gay
    -1.59
    opause
    -1.56
    áĢ¯
    -1.55
    ynes
    -1.54
     queer
    -1.47
    ikawa
    -1.47
    ussi
    -1.47
    POSITIVE LOGITS
    ives
    1.80
    imetry
    1.80
     aids
    1.68
    ément
    1.62
    pieces
    1.58
     corre
    1.50
    erior
    1.49
     Gri
    1.46
    óg
    1.45
    ive
    1.44
    Activations Density 8.339%

    No Known Activations