© 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. 27854
    Prev
    Next
    INDEX
    Explanations

    statistical data or numerical values related to measurements or quantities

    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
    369
    +0.22
    1.2%
    81
    +0.14
    0.8%
    51
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.22
    0.08
    483
    +0.14
    0.07
    477
    +0.13
    0.07
    Negative Logits
    ollah
    -1.62
    NOTES
    -1.59
    ETHOD
    -1.50
    àµį
    -1.45
    inates
    -1.45
    ¢
    -1.44
    mail
    -1.43
    ¿
    -1.42
     anybody
    -1.42
    haven
    -1.41
    POSITIVE LOGITS
    nd
    2.35
     dozen
    1.96
    ceeding
    1.64
     adult
    1.58
    plic
    1.56
    iso
    1.55
    dp
    1.55
    kc
    1.54
    ced
    1.50
    gether
    1.50
    Activations Density 0.382%

    No Known Activations