© 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. 23392
    Prev
    Next
    INDEX
    Explanations

    references to regulatory frameworks or contractual agreements

    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
    156
    +0.13
    0.7%
    337
    +0.13
    0.7%
    323
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.03
    337
    +0.13
    0.02
    489
    +0.12
    0.02
    Negative Logits
    :]
    -1.71
    :</
    -1.69
    :_
    -1.63
    :*
    -1.61
     analyt
    -1.60
    *:
    -1.54
    :[
    -1.54
    ameters
    -1.53
     deviation
    -1.48
    :`
    -1.46
    POSITIVE LOGITS
    Ļª
    3.22
    ĨĴ
    2.74
    ĭ
    2.59
    ĥ½
    2.54
    »
    2.44
    2.41
    ↵↵
    2.41
    <|outofrange|>
    2.41
    č↵
    2.41
    2.41
    Activations Density 0.359%

    No Known Activations