© 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. 11419
    Prev
    Next
    INDEX
    Explanations

    terms related to economic indicators and real estate metrics

    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
    131
    +0.16
    0.9%
    406
    +0.15
    0.8%
    245
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.16
    0.07
    131
    +0.15
    0.07
    245
    +0.12
    0.03
    Negative Logits
    ĥ½
    -2.36
    ĻĤ
    -2.31
    ↵
    -2.06
    ↵
    -2.06
    -2.06
    -2.06
    ↵
    -2.06
    <|outofrange|>
    -2.06
    ↵
    -2.06
    ↵
    -2.06
    POSITIVE LOGITS
     increased
    2.75
     decline
    2.72
     decreased
    2.72
     declining
    2.59
     decrease
    2.59
     plum
    2.57
     increase
    2.56
     increasing
    2.49
     decreasing
    2.48
     rises
    2.45
    Activations Density 0.828%

    No Known Activations