© 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. 26734
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "arise," indicating the presentation of events or situations

    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
    +0.22
    1.2%
    380
    +0.13
    0.7%
    268
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.22
    0.01
    380
    +0.13
    0.01
    316
    +0.13
    0.01
    Negative Logits
    ÄŁ
    -1.59
    sworth
    -1.38
    iser
    -1.38
    author
    -1.37
    ought
    -1.37
    ord
    -1.33
     resources
    -1.32
    âĢIJ
    -1.30
    arse
    -1.30
    schen
    -1.30
    POSITIVE LOGITS
    rogens
    2.06
    burg
    1.67
    ±
    1.49
    esis
    1.47
    tons
    1.45
     adulthood
    1.44
    ¯
    1.42
    Īĺ
    1.41
     out
    1.38
    ĨĴ
    1.37
    Activations Density 0.009%

    No Known Activations