© 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. 29486
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in a structured data format

    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
    0.9%
    303
    +0.11
    0.7%
    499
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.15
    0.04
    499
    +0.11
    0.04
    340
    +0.11
    0.04
    Negative Logits
    ously
    -2.27
    ======
    -1.78
    biz
    -1.63
    ishly
    -1.57
    urt
    -1.56
     Animation
    -1.56
    ous
    -1.52
    craft
    -1.52
    pid
    -1.51
    its
    -1.50
    POSITIVE LOGITS
     closet
    1.74
    leans
    1.65
     Marshal
    1.65
     compartment
    1.47
     "",
    1.43
    lining
    1.42
     strict
    1.39
     ibid
    1.37
     "^
    1.34
     restrictive
    1.32
    Activations Density 0.104%

    No Known Activations