© 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. 24509
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or regulatory processes

    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
    503
    +0.14
    0.8%
    12
    +0.11
    0.6%
    342
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.14
    0.02
    177
    +0.11
    0.01
    261
    +0.11
    0.00
    Negative Logits
     publishers
    -1.87
     publisher
    -1.67
     roy
    -1.66
     exclus
    -1.62
     fiction
    -1.60
     competition
    -1.55
     promoters
    -1.53
     literacy
    -1.52
     contributors
    -1.50
     novels
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.75
    IJ
    2.28
    ĨĴ
    1.89
    Īĺ
    1.84
    ľĵ
    1.75
    throws
    1.75
    ¦
    1.72
    Ĥ¬
    1.72
    ks
    1.66
    ¯
    1.63
    Activations Density 0.127%

    No Known Activations