© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "IRE"

    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
    16
    +0.12
    0.7%
    125
    +0.11
    0.6%
    394
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.12
    0.01
    389
    +0.11
    0.01
    394
    +0.11
    0.01
    Negative Logits
    UGH
    -1.69
     everything
    -1.52
    augh
    -1.52
     Appellees
    -1.49
     distance
    -1.44
     reply
    -1.41
     Respondents
    -1.41
    hers
    -1.38
     caring
    -1.38
     nowhere
    -1.37
    POSITIVE LOGITS
    ģ
    2.66
    Ģ
    2.35
    ĥ
    2.29
    ĭ
    2.16
    ¢
    2.13
    ↵            ↵
    2.12
    ↵
    2.12
    ↵  ³³³
    2.12
    ↵↵
    2.12
    ↵
    2.12
    Activations Density 1.590%

    No Known Activations