© 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 EvalsExportsAPI 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. 29238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating experience or expertise

    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
    156
    +0.21
    1.2%
    376
    +0.16
    0.9%
    8
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.21
    0.01
    479
    +0.16
    0.01
    8
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.62
    ¯
    -2.59
    ĻĤ
    -2.51
    ·¸
    -2.43
    ³
    -2.41
    ¼
    -2.40
    Ń
    -2.37
    ĵ
    -2.34
    ĺ
    -2.33
    Ļ
    -2.29
    POSITIVE LOGITS
    agne
    1.86
     evolves
    1.67
     predicts
    1.63
    iga
    1.55
    grounds
    1.54
     progresses
    1.51
    fficients
    1.50
    finder
    1.46
    ordo
    1.46
    "}](#
    1.45
    Activations Density 0.079%

    No Known Activations