© 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. 24171
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with legal cases or documents

    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
    128
    +0.13
    0.7%
    468
    +0.13
    0.7%
    421
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.13
    0.03
    421
    +0.13
    0.04
    479
    +0.12
    0.01
    Negative Logits
    edly
    -1.78
    quez
    -1.71
     devoted
    -1.67
     forum
    -1.54
     mailing
    -1.52
    wagen
    -1.51
    алÑĮ
    -1.47
    stadt
    -1.46
     thereof
    -1.41
     station
    -1.39
    POSITIVE LOGITS
    ritic
    1.74
    apers
    1.68
    axes
    1.53
    âĢ¦”
    1.51
     Suddenly
    1.51
    ...]
    1.51
     Everyone
    1.47
    aying
    1.46
     âĢ¦
    1.45
     Secondly
    1.45
    Activations Density 0.196%

    No Known Activations