© 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. 0-MLP-SM
    11. 26443
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Music"

    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
    +0.16
    0.9%
    173
    +0.12
    0.7%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.16
    0.02
    329
    +0.12
    0.02
    336
    +0.10
    0.02
    Negative Logits
     hers
    -1.83
     euthan
    -1.69
    TRODUCTION
    -1.56
     transgender
    -1.50
    wered
    -1.50
    ){#
    -1.47
     fallen
    -1.44
    rops
    -1.42
    azole
    -1.37
     gay
    -1.37
    POSITIVE LOGITS
    fiddle
    2.01
    istry
    1.96
    ifact
    1.68
    ific
    1.65
    strings
    1.62
     festivals
    1.60
    card
    1.59
    bank
    1.58
    ulator
    1.57
    coin
    1.56
    Activations Density 0.057%

    No Known Activations