© 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. 11864
    Prev
    Next
    INDEX
    Explanations

    locations and place names

    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
    25
    +0.18
    1.0%
    21
    +0.14
    0.8%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.18
    0.07
    250
    +0.14
    0.08
    432
    +0.11
    0.07
    Negative Logits
    Īĺ
    -8.68
    ↵↵
    -8.49
    ↵
    -8.49
    ↵↵↵
    -8.49
    -8.49
    -8.49
    -8.49
    ↵
    -8.49
    -8.49
    ↵
    -8.49
    POSITIVE LOGITS
    shire
    2.74
     City
    2.53
     County
    2.37
     Heights
    2.30
     Township
    2.29
     Springs
    2.24
     Harbor
    2.21
     suburb
    2.21
     city
    2.06
     Province
    2.05
    Activations Density 0.459%

    No Known Activations