© 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. 4-RES-SM
    11. 12951
    Prev
    Next
    INDEX
    Explanations

    references to influential jazz musicians and their works

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    266
    +0.15
    0.8%
    466
    +0.13
    0.7%
    315
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.15
    0.07
    203
    +0.13
    0.05
    445
    +0.12
    0.05
    Negative Logits
    ĥ½
    -3.72
    Īĺ
    -3.66
    ĸ´
    -3.59
    £
    -3.49
    ĻĤ
    -3.47
    ¼
    -3.46
    ©
    -3.46
    ļ
    -3.42
    §
    -3.38
    ¥
    -3.35
    POSITIVE LOGITS
     etc
    3.94
    etc
    3.03
     and
    2.95
     ...)
    2.46
     ...,
    2.27
     or
    2.22
    and
    2.05
    ...,
    1.79
     eds
    1.74
     respectively
    1.70
    Activations Density 0.551%

    No Known Activations