© 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. 29317
    Prev
    Next
    INDEX
    Explanations

    references to the name "Danny" or variations of it

    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
    +0.15
    0.9%
    465
    +0.11
    0.6%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.15
    0.01
    105
    +0.11
    0.01
    264
    +0.11
    0.01
    Negative Logits
    ĵ
    -1.63
    ¬
    -1.63
    oder
    -1.53
    Īĺ
    -1.51
    ?'
    -1.49
    ĺ
    -1.45
    ¦
    -1.43
     tout
    -1.39
    aning
    -1.37
    Ļª
    -1.37
    POSITIVE LOGITS
    istic
    1.68
    hearted
    1.59
    eries
    1.58
    card
    1.56
     Rptr
    1.53
    ké
    1.52
    cule
    1.51
    aic
    1.51
    ery
    1.50
    ee
    1.49
    Activations Density 0.011%

    No Known Activations