© 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. 2-RES-SM
    11. 30526
    Prev
    Next
    INDEX
    Explanations

    expressions of skepticism or uncertainty

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    106
    +0.13
    0.7%
    435
    +0.13
    0.7%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.13
    0.06
    198
    +0.13
    0.05
    397
    +0.12
    0.05
    Negative Logits
    ¯
    -2.73
    ł
    -2.70
    Į
    -2.69
    °
    -2.68
    ĨĴ
    -2.64
    Ļª
    -2.54
    ĻĤ
    -2.52
    Īĺ
    -2.49
    ¡
    -2.48
    ĺ
    -2.47
    POSITIVE LOGITS
    fire
    1.56
     whatsoever
    1.55
    istical
    1.54
    imation
    1.50
    ifice
    1.47
    liness
    1.46
     remaining
    1.42
    break
    1.42
     occurrence
    1.40
    sembl
    1.40
    Activations Density 0.646%

    No Known Activations