© 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. 28234
    Prev
    Next
    INDEX
    Explanations

    the word "dar" in varying 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
    369
    +0.13
    0.7%
    246
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.13
    0.01
    246
    +0.12
    0.01
    181
    +0.12
    0.01
    Negative Logits
    Ĥ¬
    -3.00
    ĺ
    -2.99
    ij
    -2.96
    ĨĴ
    -2.82
    ĵ
    -2.75
    ı
    -2.71
    Ĥ
    -2.64
    Ķ
    -2.63
    ĥ½
    -2.63
    IJ
    -2.57
    POSITIVE LOGITS
    woods
    1.84
    forge
    1.80
    dom
    1.79
    rett
    1.78
    vä
    1.74
     punches
    1.72
    wall
    1.70
    liche
    1.67
    works
    1.67
    leen
    1.67
    Activations Density 0.014%

    No Known Activations