© 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. 24088
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to music, including songs, lyrics, and vocal 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
    318
    +0.12
    0.7%
    319
    +0.12
    0.6%
    90
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.03
    90
    +0.12
    0.03
    186
    +0.10
    0.03
    Negative Logits
    ĨĴ
    -2.02
    tone
    -1.60
    ľĵ
    -1.60
    Ļª
    -1.57
     agonist
    -1.56
    ·
    -1.55
    Ļ
    -1.40
     press
    -1.40
    áĥIJ
    -1.38
    áĥĶ
    -1.37
    POSITIVE LOGITS
     mine
    1.54
    df
    1.46
    etz
    1.43
     deduct
    1.38
     herself
    1.34
    bler
    1.33
    eless
    1.30
     ]
    1.30
     deductions
    1.29
    iar
    1.28
    Activations Density 0.698%

    No Known Activations