© 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. 24312
    Prev
    Next
    INDEX
    Explanations

    relational concepts or connections in the context provided

    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
    107
    +0.11
    0.6%
    205
    +0.10
    0.6%
    379
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.11
    0.08
    222
    +0.10
    0.07
    18
    +0.10
    0.02
    Negative Logits
    Ĭ
    -5.04
             ↵
    -4.87
    ↵↵
    -4.87
    <|outofrange|>
    -4.87
    -4.87
    ↵↵
    -4.87
    <|outofrange|>
    -4.87
    -4.87
    čč
    -4.87
    -4.87
    POSITIVE LOGITS
     dial
    1.78
     interchange
    1.73
    ](
    1.62
     equivalents
    1.54
     administration
    1.51
     Amend
    1.48
    fulness
    1.48
     order
    1.48
    ]{},
    1.48
     ourselves
    1.47
    Activations Density 1.433%

    No Known Activations