© 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. 30426
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Oz" and to a lesser extent, references to the character "Liz."

    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
    213
    +0.15
    0.8%
    44
    +0.14
    0.8%
    74
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.15
    0.02
    71
    +0.14
    0.01
    111
    +0.11
    0.02
    Negative Logits
    itary
    -1.44
     passes
    -1.42
    sight
    -1.40
    !”
    -1.38
    ?”
    -1.37
     buildings
    -1.36
    lections
    -1.35
    cloth
    -1.33
    of
    -1.31
     walls
    -1.29
    POSITIVE LOGITS
    ¹
    3.24
    Ĵ
    3.14
    İ
    3.01
    º
    2.92
    ľĵ
    2.87
    ı
    2.87
    °
    2.83
    Į
    2.82
    ŀ
    2.81
    ļ
    2.77
    Activations Density 0.092%

    No Known Activations