© 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. 22735
    Prev
    Next
    INDEX
    Explanations

    references to performances or visual arts within text

    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
    +0.23
    1.3%
    38
    +0.12
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.23
    0.11
    18
    +0.12
    0.05
    446
    +0.12
    0.05
    Negative Logits
              ↵
    -2.32
    -2.32
     ↵
    -2.32
    ↵
    -2.32
    ↵
    -2.32
    -2.32
    -2.32
    ↵
    -2.32
    ↵
    -2.32
    ↵
    -2.32
    POSITIVE LOGITS
    ostatic
    1.66
     discharg
    1.58
    ]{.
    1.58
     gaug
    1.57
     intervals
    1.49
     adj
    1.44
     folds
    1.43
     Amend
    1.38
     =&
    1.36
    asone
    1.35
    Activations Density 1.344%

    No Known Activations