© 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. 2-RES-SM
    11. 9557
    Prev
    Next
    INDEX
    Explanations

    periods or sentence endings

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    111
    +0.59
    4.9%
    156
    +0.54
    4.4%
    56
    +0.14
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.59
    0.73
    156
    +0.54
    0.63
    71
    +0.14
    0.60
    Negative Logits
    ħ
    -5.37
    ij
    -4.89
    ¿½
    -4.84
    Ŀ
    -4.84
    ķ
    -4.76
    Ħ
    -4.74
    Ģ
    -4.71
    ľ
    -4.66
    Į
    -4.64
    ŀ
    -4.62
    POSITIVE LOGITS
     wow
    1.41
     fans
    1.38
     vibe
    1.30
     spirits
    1.29
     winning
    1.26
     morale
    1.25
     fundament
    1.24
     appeal
    1.24
     fuck
    1.21
    angered
    1.19
    Activations Density 0.886%

    No Known Activations