© 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. 25539
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the word "this."

    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
    402
    +0.13
    0.8%
    365
    +0.13
    0.7%
    56
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.10
    127
    +0.13
    0.10
    199
    +0.12
    0.09
    Negative Logits
    Ļª
    -2.59
    Ĩ
    -2.41
    ħ
    -2.37
    ļ
    -2.32
    İ
    -2.32
    ¯
    -2.31
    µ
    -2.27
    ·¸
    -2.26
    Ŀ
    -2.25
    Ģ
    -2.25
    POSITIVE LOGITS
     kind
    2.04
     happen
    1.94
     happened
    1.93
     happ
    1.91
     happens
    1.76
     morning
    1.63
     sort
    1.61
     sorts
    1.55
     yours
    1.54
    happ
    1.53
    Activations Density 0.562%

    No Known Activations