© 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. 28779
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    145
    +0.14
    0.8%
    12
    +0.12
    0.7%
    448
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.14
    0.03
    145
    +0.12
    0.03
    81
    +0.12
    0.02
    Negative Logits
    ¿½
    -4.07
    ķ
    -3.80
    ¡
    -3.75
    Īĺ
    -3.71
               ↵
    -3.65
    ↵
    -3.65
    ↵
    -3.65
    č↵č↵
    -3.65
    -3.65
    ↵↵
    -3.65
    POSITIVE LOGITS
    ienn
    1.51
    acter
    1.49
    unreadable
    1.48
    ×Ŀ
    1.45
    orage
    1.44
    istory
    1.43
    ISON
    1.38
     Authority
    1.37
    cyst
    1.35
    witz
    1.32
    Activations Density 0.132%

    No Known Activations