© 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. 25737
    Prev
    Next
    INDEX
    Explanations

    statements expressing mixed feelings about a situation

    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
    17
    +0.14
    0.8%
    216
    +0.12
    0.7%
    97
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.09
    216
    +0.12
    0.12
    348
    +0.11
    0.17
    Negative Logits
    ·
    -2.00
    ľ
    -1.89
    documentclass
    -1.85
    ¯
    -1.82
     respectively
    -1.82
    atively
    -1.74
    apine
    -1.73
    µ
    -1.70
    Ĺ
    -1.67
    Ħ
    -1.66
    POSITIVE LOGITS
    izen
    1.70
    enties
    1.43
    rio
    1.42
    erto
    1.42
    cis
    1.38
     ecosystem
    1.37
    vier
    1.35
     depend
    1.35
    ite
    1.31
     Rptr
    1.30
    Activations Density 8.091%

    No Known Activations