© 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. 30165
    Prev
    Next
    INDEX
    Explanations

    references to surgical procedures

    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
    +0.31
    1.9%
    184
    +0.13
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.02
    102
    +0.13
    0.01
    103
    +0.12
    0.01
    Negative Logits
     Publ
    -1.50
    amy
    -1.50
    ı
    -1.44
    že
    -1.40
    ÑĶ
    -1.39
    ene
    -1.38
     happier
    -1.37
    ager
    -1.37
    ĨĴ
    -1.37
    ķ
    -1.36
    POSITIVE LOGITS
    mission
    1.79
     accounting
    1.58
    miss
    1.55
    pose
    1.47
    hoc
    1.46
     emergencies
    1.45
     regimes
    1.44
     now
    1.41
    ettes
    1.40
     appointments
    1.37
    Activations Density 0.044%

    No Known Activations