© 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. 26411
    Prev
    Next
    INDEX
    Explanations

    the word "including."

    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
    129
    +0.20
    1.2%
    376
    +0.19
    1.1%
    334
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.20
    0.01
    62
    +0.19
    0.02
    316
    +0.13
    0.01
    Negative Logits
    ®
    -2.39
    Ĵ
    -2.10
    ī
    -1.98
    &
    -1.94
    ĨĴ
    -1.90
    ´
    -1.72
    Ħ
    -1.70
     &
    -1.70
    ĵ
    -1.61
    ¬
    -1.59
    POSITIVE LOGITS
    ages
    1.61
    inib
    1.54
    iders
    1.54
    tered
    1.51
    cibly
    1.49
    appropri
    1.47
    ovir
    1.46
    aker
    1.43
    comings
    1.43
    cible
    1.41
    Activations Density 0.021%

    No Known Activations