© 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. 27770
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the absence of something

    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
    478
    +0.19
    1.1%
    376
    +0.14
    0.8%
    354
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.19
    0.04
    424
    +0.14
    0.04
    211
    +0.10
    0.03
    Negative Logits
    Ŀ
    -1.62
    ume
    -1.55
    ľ
    -1.53
    utors
    -1.52
    eth
    -1.50
    responsible
    -1.49
    ¸
    -1.48
    §
    -1.48
    ±
    -1.47
    sound
    -1.47
    POSITIVE LOGITS
     respect
    1.90
     regard
    1.76
     undue
    1.76
     restrictions
    1.60
     restriction
    1.56
     sacrific
    1.55
     luck
    1.53
     remar
    1.52
     any
    1.51
    ULAR
    1.49
    Activations Density 0.244%

    No Known Activations