© 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. 2-MLP-SM
    11. 23682
    Prev
    Next
    INDEX
    Explanations

    references to films and movies

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    68
    +0.11
    0.6%
    327
    +0.11
    0.6%
    386
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.11
    0.02
    493
    +0.11
    0.02
    457
    +0.10
    0.01
    Negative Logits
    imer
    -1.50
     merits
    -1.36
     Honorable
    -1.34
    >&
    -1.33
     ferment
    -1.33
     iron
    -1.32
    gged
    -1.32
     shone
    -1.31
    ashi
    -1.31
     cheek
    -1.29
    POSITIVE LOGITS
    àµį
    1.59
    à¯ģ
    1.59
    à¯
    1.57
    $.[]{
    1.56
    àµ
    1.55
    harm
    1.50
    ி
    1.46
    cels
    1.39
    ropri
    1.37
    PLIED
    1.36
    Activations Density 0.177%

    No Known Activations