© 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. 30555
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the term "Mail" in various contexts, potentially related to email or communication

    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
    1
    +0.13
    0.7%
    457
    +0.13
    0.7%
    250
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.13
    0.01
    347
    +0.13
    0.01
    392
    +0.12
    0.01
    Negative Logits
     pregnant
    -1.70
     hers
    -1.61
    "?
    -1.54
     authors
    -1.53
     yours
    -1.52
     dear
    -1.51
     labor
    -1.50
    antly
    -1.50
     exceeding
    -1.48
     similar
    -1.48
    POSITIVE LOGITS
    °
    2.13
    aña
    1.94
    ¾
    1.92
    vist
    1.92
    bridge
    1.85
    achusetts
    1.80
    ª
    1.79
    uximab
    1.78
    ¢
    1.77
    ĻĤ
    1.76
    Activations Density 0.007%

    No Known Activations