© 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. 0-MLP-SM
    11. 28829
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Metropolitan."

    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
    156
    +0.20
    1.1%
    71
    +0.13
    0.7%
    454
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.01
    340
    +0.13
    0.01
    327
    +0.12
    0.01
    Negative Logits
     violent
    -1.63
     conscience
    -1.60
     massive
    -1.57
     sudden
    -1.53
    ying
    -1.51
     different
    -1.50
     true
    -1.47
     permanent
    -1.47
     horrible
    -1.43
     dramatic
    -1.41
    POSITIVE LOGITS
    Īĺ
    2.11
    ató
    1.86
    ł
    1.79
    opan
    1.74
    ¨
    1.71
    ĻĤ
    1.70
    º
    1.63
    umns
    1.62
    ĭ
    1.61
    film
    1.60
    Activations Density 0.015%

    No Known Activations