© 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. 23654
    Prev
    Next
    INDEX
    Explanations

    words related to musical elements or performances

    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
    23
    +0.25
    1.4%
    271
    +0.17
    1.0%
    332
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.25
    0.11
    332
    +0.17
    0.14
    458
    +0.14
    0.08
    Negative Logits
    ↵↵↵
    -1.67
    ↵
    -1.67
    <|outofrange|>
    -1.67
    -1.67
    ↵
    -1.67
    ↵
    -1.67
    ↵
    -1.67
    -1.67
    -1.67
    <|outofrange|>
    -1.67
    POSITIVE LOGITS
    ÑĥÑĤ
    1.54
    antically
    1.51
    Ö
    1.51
    иÑĢ
    1.48
    Ûķ
    1.48
    ÙĪد
    1.47
    енÑĤ
    1.46
    ÑĢÑĭ
    1.46
    ãģļ
    1.46
     zombie
    1.46
    Activations Density 1.487%

    No Known Activations