© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25189
    Prev
    Next
    INDEX
    Explanations

    encoded terms related to encryption protocols

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    444
    +0.14
    0.8%
    111
    +0.12
    0.7%
    108
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.14
    0.01
    108
    +0.12
    0.01
    336
    +0.11
    0.01
    Negative Logits
    ³
    -2.03
    Ĥ
    -1.99
    Ĺ
    -1.87
    ¦
    -1.79
    ¿
    -1.77
    ·
    -1.72
    Ł
    -1.66
    soever
    -1.61
    »
    -1.61
    ¼
    -1.58
    POSITIVE LOGITS
    ilio
    1.96
    enos
    1.83
    ieux
    1.73
    :`
    1.73
    etts
    1.65
    illo
    1.63
    arroll
    1.61
    INA
    1.57
    etable
    1.56
    iedad
    1.55
    Activations Density 0.014%

    No Known Activations