© 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. 1-RES-SM
    11. 25927
    Prev
    Next
    INDEX
    Explanations

    references to different high schools and their attributes

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    365
    +0.14
    0.8%
    451
    +0.11
    0.6%
    259
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.03
    84
    +0.11
    0.03
    284
    +0.10
    0.03
    Negative Logits
    ¶
    -3.36
    IJ
    -3.33
    ĨĴ
    -3.14
    ±
    -3.12
    ĥ½
    -3.12
    ¯
    -3.03
    į
    -2.96
    Ĵ
    -2.95
    ·
    -2.92
    ¦
    -2.91
    POSITIVE LOGITS
     Athletic
    1.88
    ward
    1.88
    ships
    1.80
     professor
    1.77
     Career
    1.65
     championships
    1.64
     career
    1.62
     sports
    1.60
     offers
    1.55
     Premier
    1.55
    Activations Density 0.277%

    No Known Activations