© 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. Residuals
    9. 2-RES-SM
    11. 12923
    Prev
    Next
    INDEX
    Explanations

    references to subjects in academic or research contexts

    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
    372
    +0.18
    1.0%
    156
    +0.17
    1.0%
    365
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.18
    0.03
    365
    +0.17
    0.02
    184
    +0.14
    0.01
    Negative Logits
    ĥ½
    -2.88
    Ļ
    -2.60
    Ħ
    -2.58
    ı
    -2.51
    Ĵ
    -2.50
    Ĥ¬
    -2.48
    ŀ
    -2.42
    ¬
    -2.31
    ¿½
    -2.26
    °
    -2.25
    POSITIVE LOGITS
    matter
    1.69
    ivity
    1.64
    ive
    1.62
     who
    1.61
    ights
    1.57
    ively
    1.55
    sit
    1.52
    iscus
    1.51
    cels
    1.51
    aven
    1.49
    Activations Density 0.083%

    No Known Activations