© 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. 28768
    Prev
    Next
    INDEX
    Explanations

    quoted text or sections from documents

    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
    69
    +0.16
    0.9%
    342
    +0.15
    0.9%
    174
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.16
    0.08
    340
    +0.15
    0.07
    261
    +0.12
    0.06
    Negative Logits
    Ļª
    -1.95
    ·
    -1.67
    ¿½
    -1.65
     scale
    -1.61
    ·¸
    -1.58
    estry
    -1.55
    ¥
    -1.50
    ĨĴ
    -1.47
    oscope
    -1.46
    scale
    -1.44
    POSITIVE LOGITS
    kte
    1.70
    tered
    1.67
    igin
    1.58
    igan
    1.50
    igation
    1.50
    verex
    1.47
    ilian
    1.47
    ig
    1.43
    ably
    1.42
    nen
    1.41
    Activations Density 0.061%

    No Known Activations