© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    general identifiers and keywords related to business and products

    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
    +0.17
    0.9%
    414
    +0.12
    0.6%
    305
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.05
    316
    +0.12
    0.10
    491
    +0.10
    0.06
    Negative Logits
     excel
    -1.55
     databases
    -1.48
    launchpad
    -1.47
    starter
    -1.42
     honor
    -1.41
     libraries
    -1.41
     coff
    -1.41
     alt
    -1.38
     aside
    -1.36
    gie
    -1.36
    POSITIVE LOGITS
    ration
    1.65
    igraph
    1.54
    asted
    1.52
    ¶
    1.49
    imet
    1.43
    ł
    1.37
    ctomy
    1.36
    imeter
    1.35
    ifiable
    1.33
    âĪ¶
    1.32
    Activations Density 2.088%

    No Known Activations