© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    instances of the word "performed."

    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
    +0.19
    1.1%
    148
    +0.13
    0.8%
    485
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.19
    0.02
    485
    +0.13
    0.02
    167
    +0.12
    0.02
    Negative Logits
    ĨĴ
    -2.70
    ĥ½
    -2.08
    Ĵ
    -2.07
    Ļª
    -1.74
    §
    -1.72
    ģ
    -1.72
    ŀ
    -1.66
    ¼
    -1.63
    ré
    -1.63
    ĩ
    -1.62
    POSITIVE LOGITS
    ipes
    1.67
    pez
    1.66
    ont
    1.63
    evil
    1.59
    erals
    1.52
    odies
    1.52
    irection
    1.48
    lasses
    1.44
    iece
    1.43
    ictor
    1.43
    Activations Density 1.589%

    No Known Activations