© 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. 1-RES-SM
    11. 29151
    Prev
    Next
    INDEX
    Explanations

    documentation-related language and code structures

    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
    478
    +0.15
    0.8%
    269
    +0.13
    0.7%
    246
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.15
    271
    +0.13
    0.06
    156
    +0.13
    0.07
    Negative Logits
    eners
    -1.81
    ness
    -1.54
    amente
    -1.54
    inez
    -1.53
    ttes
    -1.51
    apine
    -1.49
     Academy
    -1.49
    ament
    -1.47
    ipe
    -1.45
     commission
    -1.45
    POSITIVE LOGITS
    ¦
    2.66
    ¼
    2.54
    ¡
    2.46
    Īĺ
    2.44
      ↵
    2.40
    2.40
    2.40
    2.40
    ↵
    2.40
      ↵
    2.40
    Activations Density 0.463%

    No Known Activations