© 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 EvalsExportsAPI 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. 28482
    Prev
    Next
    INDEX
    Explanations

    specific chemical substances and compounds, particularly different types of alcohol and their derivatives

    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
    446
    +0.15
    0.9%
    227
    +0.12
    0.7%
    105
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.15
    0.01
    446
    +0.12
    0.01
    227
    +0.12
    0.01
    Negative Logits
    ureus
    -1.57
    edes
    -1.53
    quired
    -1.41
    RESULTS
    -1.35
    ecause
    -1.32
    ede
    -1.31
     Fla
    -1.30
    opic
    -1.29
     accordance
    -1.29
    «
    -1.29
    POSITIVE LOGITS
    ¥
    2.21
    ¢
    1.96
    ĻĤ
    1.93
    ²
    1.92
    ®
    1.82
    ļ
    1.81
    ª
    1.77
    ¡
    1.75
    ¹
    1.69
    ome
    1.68
    Activations Density 0.007%

    No Known Activations