© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11645
    Prev
    Next
    INDEX
    Explanations

    occurrences of the left parenthesis symbol

    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
    156
    +0.13
    0.7%
    240
    +0.12
    0.7%
    350
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.13
    0.04
    200
    +0.12
    0.04
    340
    +0.12
    0.03
    Negative Logits
     Activities
    -1.74
     License
    -1.67
    ycin
    -1.64
     Notes
    -1.58
     issue
    -1.55
     Parameters
    -1.54
     notes
    -1.51
     remarks
    -1.50
     SOFTWARE
    -1.48
     Cookies
    -1.47
    POSITIVE LOGITS
    5.12
    5.12
    ↵
    5.12
    ↵
    5.12
          ↵
    5.12
    5.12
    5.12
    <|outofrange|>
    5.12
    ↵
    5.12
    ↵
    5.12
    Activations Density 0.170%

    No Known Activations