© 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. 0-MLP-SM
    11. 26422
    Prev
    Next
    INDEX
    Explanations

    mentions of governors

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    59
    +0.14
    0.8%
    410
    +0.13
    0.8%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.14
    0.02
    403
    +0.13
    0.01
    59
    +0.13
    0.01
    Negative Logits
    Ļª
    -1.78
     BGCOLOR
    -1.75
     Collaboration
    -1.53
    aspx
    -1.45
    ESULT
    -1.45
    ubert
    -1.42
    etermined
    -1.41
    iscuss
    -1.39
    yz
    -1.38
     Secondly
    -1.37
    POSITIVE LOGITS
    orov
    1.81
    zilla
    1.67
    arie
    1.64
    ariate
    1.62
    orial
    1.56
     channels
    1.55
     aside
    1.54
    elled
    1.53
    ’
    1.52
    tons
    1.49
    Activations Density 0.209%

    No Known Activations