© 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. Residuals
    9. 2-RES-SM
    11. 9982
    Prev
    Next
    INDEX
    Explanations

    references to music albums and songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    156
    +0.14
    0.8%
    100
    +0.13
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.14
    0.03
    462
    +0.13
    0.01
    341
    +0.11
    0.02
    Negative Logits
    ¯
    -2.35
    ĥ½
    -2.32
    Ł
    -2.30
    ı
    -2.19
    Ĩ
    -2.16
    Ĵ
    -2.13
    ↵
    -2.08
    ↵
    -2.08
    <|outofrange|>
    -2.08
    č↵
    -2.08
    POSITIVE LOGITS
     sung
    1.96
     record
    1.90
     title
    1.80
     titles
    1.80
     lyrics
    1.73
     featuring
    1.73
    recorded
    1.72
    record
    1.71
     opener
    1.70
    erg
    1.69
    Activations Density 0.103%

    No Known Activations