© 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. 26697
    Prev
    Next
    INDEX
    Explanations

    references to significant or recognized names within a specific context

    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
    59
    +0.13
    0.8%
    467
    +0.12
    0.7%
    378
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.13
    0.01
    318
    +0.12
    0.01
    330
    +0.12
    0.01
    Negative Logits
    ĸ´
    -2.40
     affairs
    -2.28
    Ĥ¬
    -1.97
    ĨĴ
    -1.83
    Īĺ
    -1.80
    »¿
    -1.79
    Ĥ
    -1.77
     arranged
    -1.72
    Ļª
    -1.69
    tering
    -1.68
    POSITIVE LOGITS
    ostic
    1.68
    ardi
    1.60
    omencl
    1.54
     factor
    1.53
    recht
    1.52
    TF
    1.50
    aceae
    1.49
    atz
    1.48
    etics
    1.47
     factors
    1.47
    Activations Density 0.123%

    No Known Activations