© 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. 29139
    Prev
    Next
    INDEX
    Explanations

    references to "zip" codes or related terms

    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
    487
    +0.14
    0.8%
    376
    +0.12
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.14
    0.01
    143
    +0.12
    0.01
    437
    +0.12
    0.01
    Negative Logits
    ł
    -2.25
    ĸ´
    -2.15
    ľĵ
    -2.08
    §
    -2.06
    ĵ
    -1.94
    Ļª
    -1.94
    Ĭ
    -1.94
    ´
    -1.89
    ¨
    -1.87
    ĥ½
    -1.82
    POSITIVE LOGITS
    iju
    1.74
    codes
    1.71
    rio
    1.70
    lei
    1.70
    orro
    1.67
    metal
    1.65
    pered
    1.65
    maker
    1.62
    hart
    1.60
    heed
    1.60
    Activations Density 0.404%

    No Known Activations