© 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. 26082
    Prev
    Next
    INDEX
    Explanations

    mentions of infrastructure

    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
    +0.24
    1.5%
    365
    +0.13
    0.8%
    460
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.24
    0.02
    451
    +0.13
    0.01
    365
    +0.12
    0.01
    Negative Logits
    §
    -2.51
    ĥ½
    -2.48
    Ń
    -2.09
    Ŀ
    -2.06
    ı
    -2.05
    Ī
    -2.04
    º
    -1.95
    ĥ
    -1.94
    ¬
    -1.93
    ĩ
    -1.92
    POSITIVE LOGITS
     surrounds
    1.90
     consists
    1.89
     appears
    1.77
    ically
    1.74
     follows
    1.70
    blocks
    1.67
    frame
    1.63
     exists
    1.59
    isms
    1.58
     controls
    1.58
    Activations Density 0.011%

    No Known Activations