© 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. 28425
    Prev
    Next
    INDEX
    Explanations

    references to plugins

    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
    +0.23
    1.4%
    376
    +0.15
    1.0%
    217
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.23
    0.01
    217
    +0.15
    0.01
    14
    +0.13
    0.01
    Negative Logits
    §
    -2.24
    ©
    -2.17
    ĥ½
    -2.15
    ı
    -2.01
    ±
    -1.92
    ¸
    -1.88
    ¨
    -1.83
    woke
    -1.82
    ĥ
    -1.79
    ¬
    -1.79
    POSITIVE LOGITS
    #:
    1.86
    emis
    1.81
    pora
    1.77
    ificate
    1.73
    ambers
    1.71
    bill
    1.71
    birds
    1.70
    fors
    1.69
    guns
    1.68
    nant
    1.66
    Activations Density 0.008%

    No Known Activations