© 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. 22982
    Prev
    Next
    INDEX
    Explanations

    phrases related to media productions and programming announcements

    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
    407
    +0.14
    0.8%
    2
    +0.11
    0.6%
    3
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.14
    0.11
    135
    +0.11
    0.07
    108
    +0.11
    0.11
    Negative Logits
    INGTON
    -1.69
     talk
    -1.63
    '>
    -1.58
     sunshine
    -1.54
     silence
    -1.48
     breathe
    -1.47
     whispers
    -1.41
     APPEALS
    -1.39
     BGCOLOR
    -1.37
     heart
    -1.37
    POSITIVE LOGITS
    ets
    1.66
    itories
    1.53
    liga
    1.53
    heets
    1.48
    pace
    1.46
    ului
    1.45
    ais
    1.42
    efs
    1.39
     suitable
    1.39
    citations
    1.39
    Activations Density 2.036%

    No Known Activations