© 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. 1-RES-SM
    11. 27336
    Prev
    Next
    INDEX
    Explanations

    references to the Gulf region or related 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
    111
    +0.13
    0.7%
    304
    +0.13
    0.7%
    314
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.13
    0.02
    304
    +0.13
    0.02
    314
    +0.13
    0.02
    Negative Logits
     attend
    -1.87
     learned
    -1.72
     superv
    -1.68
     nurse
    -1.67
     coordinate
    -1.63
     meeting
    -1.58
     follow
    -1.56
     promise
    -1.55
     schedule
    -1.54
     few
    -1.54
    POSITIVE LOGITS
    §
    2.56
    2.50
    2.50
    č↵
    2.50
    <|outofrange|>
    2.50
    2.50
    ↵
    2.50
    ↵↵↵
    2.50
    2.50
    ↵↵
    2.50
    Activations Density 0.152%

    No Known Activations