© 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. 4-RES-SM
    11. 12701
    Prev
    Next
    INDEX
    Explanations

    instances of code or symbols typically used in programming languages

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    271
    +0.12
    0.7%
    78
    +0.12
    0.7%
    321
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.00
    21
    +0.12
    0.01
    388
    +0.11
    0.01
    Negative Logits
    izations
    -1.60
     ‘
    -1.55
    izing
    -1.52
     inheritance
    -1.48
     “
    -1.47
    ting
    -1.44
     succession
    -1.43
     hij
    -1.43
    atically
    -1.43
    izers
    -1.40
    POSITIVE LOGITS
    ´
    3.92
    ¶
    3.71
    ¸
    3.68
    ĥ
    3.59
    ±
    3.58
    ¯
    3.55
    Ĭ
    3.54
    ½
    3.53
    ↵
    3.49
    ↵
    3.49
    Activations Density 0.023%

    No Known Activations