© 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. 2-MLP-SM
    11. 24258
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to hypotheses or proposed theories

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    459
    +0.14
    0.8%
    155
    +0.12
    0.6%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.14
    0.04
    283
    +0.12
    0.04
    335
    +0.10
    0.04
    Negative Logits
     doom
    -1.62
    ÑıÑĤ
    -1.46
    agt
    -1.40
    ());
    -1.35
     fever
    -1.31
    oxygen
    -1.30
     alright
    -1.30
     offence
    -1.29
     disaster
    -1.26
     wrath
    -1.25
    POSITIVE LOGITS
     âĢķ
    1.78
    itat
    1.71
    zione
    1.70
     quo
    1.60
    âĪ¶
    1.57
    \][
    1.56
    .^[@
    1.51
    ÂĴ
    1.50
    ableness
    1.48
    ierno
    1.47
    Activations Density 0.157%

    No Known Activations