© 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. 25594
    Prev
    Next
    INDEX
    Explanations

    code-related components and operations, especially those involving data structures and manipulation in programming 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/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
    156
    +0.28
    1.6%
    151
    +0.13
    0.7%
    165
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.28
    0.07
    151
    +0.13
    0.05
    17
    +0.13
    0.02
    Negative Logits
    ↵
    -4.22
    -4.22
    ↵
    -4.22
    č↵
    -4.22
    ↵
    -4.22
          ↵
    -4.22
    ↵↵
    -4.22
    -4.22
    -4.22
    -4.22
    POSITIVE LOGITS
     again
    1.75
     yourself
    1.72
    ?",
    1.66
    '?"
    1.56
    =%
    1.53
     ?"
    1.51
     Pradesh
    1.46
     himself
    1.44
    :"
    1.44
     yourselves
    1.43
    Activations Density 0.631%

    No Known Activations