© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and storytelling

    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
    190
    +0.12
    0.7%
    465
    +0.12
    0.6%
    493
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.12
    95
    +0.12
    0.11
    2
    +0.12
    0.10
    Negative Logits
    ĻĤ
    -2.21
    Īĺ
    -1.79
    ¯
    -1.62
    ¦
    -1.60
    º
    -1.56
     tour
    -1.55
    ij
    -1.54
    ŀ
    -1.54
    ±
    -1.53
    ↵
    -1.53
    POSITIVE LOGITS
    "));
    1.71
    ign
    1.63
    '));
    1.63
    ).)
    1.59
    asts
    1.59
    omb
    1.58
    adesh
    1.57
    ift
    1.56
    ocket
    1.55
    uracy
    1.54
    Activations Density 2.475%

    No Known Activations