© 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. 11247
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be," indicating states or conditions

    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
    +0.14
    0.8%
    348
    +0.14
    0.8%
    216
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.14
    0.08
    23
    +0.14
    0.07
    289
    +0.13
    0.04
    Negative Logits
    ¼
    -3.16
    ↵
    -3.03
    <|outofrange|>
    -3.03
    <|outofrange|>
    -3.03
    ↵  âĢĥ
    -3.03
    -3.03
    ↵
    -3.03
    ↵
    -3.03
    ↵↵
    -3.03
    ↵
    -3.03
    POSITIVE LOGITS
     trademarks
    2.13
     enumerated
    1.87
     alike
    1.85
     covariates
    1.81
     summarized
    1.77
     mutually
    1.77
     omitted
    1.76
     included
    1.73
     hereby
    1.72
     factors
    1.67
    Activations Density 0.365%

    No Known Activations