© 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 EvalsExportsAPI 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. 24444
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental authority and its actions

    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
    44
    +0.15
    0.8%
    266
    +0.12
    0.7%
    313
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.15
    0.11
    44
    +0.12
    0.05
    404
    +0.12
    0.10
    Negative Logits
    kered
    -1.58
    kers
    -1.55
    liest
    -1.41
    Spring
    -1.38
    hes
    -1.36
    ker
    -1.36
    gradle
    -1.34
     */,
    -1.33
    LAND
    -1.30
    Grad
    -1.27
    POSITIVE LOGITS
     ↵
    2.61
    ↵
    2.61
    ↵
    2.61
    ↵
    2.61
    2.61
    ↵
    2.61
    č↵
    2.61
    2.61
    č↵
    2.61
    <|outofrange|>
    2.61
    Activations Density 1.215%

    No Known Activations