© 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. 30379
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and engineering

    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
    +0.17
    1.0%
    271
    +0.16
    0.9%
    186
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.17
    0.02
    172
    +0.16
    0.06
    25
    +0.14
    0.10
    Negative Logits
    rientation
    -1.80
     yourselves
    -1.54
    comes
    -1.52
     oneself
    -1.50
     yourself
    -1.49
    GREEK
    -1.45
     say
    -1.40
     further
    -1.37
     own
    -1.34
    ción
    -1.34
    POSITIVE LOGITS
    ®
    4.17
    4.15
    ↵
    4.15
    4.15
    ↵
    4.15
    4.15
    ↵            ↵
    4.15
    4.15
              ↵
    4.15
    4.15
    Activations Density 3.433%

    No Known Activations