© 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 EvalsExportsinterp-engineNEWAPI 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. 24590
    Prev
    Next
    INDEX
    Explanations

    expressions indicating readiness or preparedness

    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
    144
    +0.15
    0.8%
    268
    +0.13
    0.7%
    11
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.15
    0.03
    144
    +0.13
    0.03
    11
    +0.12
    0.03
    Negative Logits
    Ļª
    -2.69
    ĥ½
    -2.44
    §
    -2.00
    ı
    -2.00
    ©
    -1.95
    ĩ
    -1.89
    ĵ
    -1.87
    ŀ
    -1.83
    Īĺ
    -1.82
    ĨĴ
    -1.81
    POSITIVE LOGITS
    addy
    1.51
    ingly
    1.45
    eted
    1.37
    ais
    1.35
    ads
    1.34
    iator
    1.32
    emente
    1.32
    ness
    1.30
    eld
    1.29
    iative
    1.29
    Activations Density 0.121%

    No Known Activations