© 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. 26599
    Prev
    Next
    INDEX
    Explanations

    words related to essential components or elements in various contexts

    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
    376
    +0.17
    1.0%
    156
    +0.15
    0.9%
    148
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.17
    0.01
    420
    +0.15
    0.01
    209
    +0.13
    0.01
    Negative Logits
    ®
    -1.95
    Ń
    -1.74
    »
    -1.68
    ĥ½
    -1.65
    Č
    -1.65
    ½
    -1.64
    ±
    -1.60
    ³
    -1.58
    Ŀ
    -1.57
    ène
    -1.55
    POSITIVE LOGITS
    ised
    1.66
    ized
    1.59
     Parenthood
    1.55
     arts
    1.54
    essa
    1.54
    ität
    1.51
    isation
    1.50
     aspect
    1.49
    isations
    1.45
    heid
    1.43
    Activations Density 0.088%

    No Known Activations