© 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. 25906
    Prev
    Next
    INDEX
    Explanations

    phrases related to proximity or closeness

    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
    +0.13
    0.7%
    247
    +0.11
    0.6%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.13
    0.02
    86
    +0.11
    0.02
    482
    +0.11
    0.02
    Negative Logits
    §
    -2.74
    ĵ
    -2.62
    Ĵ
    -2.55
    º
    -2.52
    »¿
    -2.49
    ¹
    -2.46
    ĨĴ
    -2.42
    ©
    -2.38
    ®
    -2.34
    Ľ
    -2.31
    POSITIVE LOGITS
     than
    2.11
    Than
    1.96
     Than
    1.68
    dimen
    1.57
    dated
    1.54
     ago
    1.53
     duty
    1.47
     ('
    1.46
     inspection
    1.44
     duties
    1.43
    Activations Density 0.015%

    No Known Activations